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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4205
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and related metadata

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

    citations and academic references with numerical identifiers and bibliographic formatting.

    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
    +#+
    -0.41
     comuniques
    -0.38
    AnchorTagHelper
    -0.38
     pyplot
    -0.37
     secular
    -0.37
    Diwedd
    -0.36
     Picchu
    -0.36
    SharedDtor
    -0.35
    leetcode
    -0.35
    djangoproject
    -0.34
    POSITIVE LOGITS
     fuzzy
    0.80
     rules
    0.73
     rule
    0.71
     Fuzzy
    0.71
     expert
    0.69
     Expert
    0.66
    Expert
    0.65
    fuzzy
    0.64
    Fuzzy
    0.64
     reglas
    0.64
    Activations Density 0.476%

    No Known Activations