© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14421
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to miniaturization and compactness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Mini" in various product names, technologies, or specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "Mini" appearing in various contexts (products, devices, assessments, and technical terms).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the word "Mini" (often as part of product names, brand names, or technical terms).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to miniature size or “mini” forms, especially words using the mini- prefix to denote small versions of items or concepts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPJ
    -0.52
    addContainerGap
    -0.44
     '{@
    -0.44
     Trabalho
    -0.44
     plufieurs
    -0.44
    tagHelperRunner
    -0.44
    entibus
    -0.42
    forKey
    -0.42
     autorytatywna
    -0.42
     intermédiaire
    -0.41
    POSITIVE LOGITS
     mini
    0.87
     Mini
    0.83
    Mini
    0.82
     MINI
    0.81
    MINI
    0.71
    mini
    0.70
    ミニ
    0.69
     miniature
    0.68
     minis
    0.65
     minima
    0.62
    Activations Density 0.118%

    No Known Activations