© 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. 14493
    Prev
    Next
    INDEX
    Explanations

    statistical models and their associated effects

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

    technical terms and specialized language across different domains, particularly focusing on models, effects, and technical components.

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

    nouns that describe systems, methods, or technical concepts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    μβρίου
    -0.44
    ChildScrollView
    -0.44
    XMLHttpRequest
    -0.41
     للاسماء
    -0.40
    addPreferredGap
    -0.40
     SwitchCompat
    -0.39
    Traducción
    -0.39
     continúas
    -0.39
    WriteBarrier
    -0.37
    forChild
    -0.36
    POSITIVE LOGITS
     them
    1.08
     your
    0.87
     him
    0.85
    them
    0.77
     their
    0.66
     Ihren
    0.66
     THEM
    0.66
     yourself
    0.65
     zichzelf
    0.64
     yourselves
    0.63
    Activations Density 0.726%

    No Known Activations