© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1798
    Prev
    Next
    INDEX
    Explanations

    references to code annotations and documentation style comments

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

    javadoc and code documentation comments with parameter and return type annotations.

    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
     referrerpolicy
    -0.39
    aarrggbb
    -0.39
    󠁣
    -0.37
    Linki
    -0.35
    soort
    -0.34
    Ārējās
    -0.33
    ękuję
    -0.32
    <()>
    -0.31
     Abweich
    -0.31
     nõ
    -0.31
    POSITIVE LOGITS
     @
    1.14
    @
    0.87
    (@
    0.73
    :@
    0.70
     @_
    0.69
     $@
    0.68
    :@
    0.67
    @
    0.66
     (@
    0.65
     @$
    0.61
    Activations Density 0.110%

    No Known Activations