© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    function call assertions and parameter checks in code

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

    assignment operations using the equals sign in code.

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

    variable assignments and initialization statements in code.

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

    programming code snippets, especially assignment and return statements with typical syntax/punctuation across languages.

    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
     fieltro
    -0.46
     argint
    -0.44
     liné
    -0.42
     vientre
    -0.41
     ganchillo
    -0.41
     silicona
    -0.40
     băr
    -0.39
    delwed
    -0.39
     păr
    -0.37
    érieur
    -0.37
    POSITIVE LOGITS
    (_
    0.84
    =_
    0.77
     $_
    0.71
     (_
    0.69
     _
    0.69
    [_
    0.68
    :_
    0.67
     {_
    0.63
    ".$_
    0.63
     [_
    0.60
    Activations Density 0.284%

    No Known Activations