© 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. 35-GEMMASCOPE-RES-16K
    6. 6539
    Prev
    Next
    INDEX
    Explanations

    functions and method calls in programming or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NULL
    -0.34
     super
    -0.32
     joys
    -0.28
    squeeze
    -0.28
    NULL
    -0.27
    setContentView
    -0.26
     itself
    -0.25
    ValueError
    -0.25
     del
    -0.25
     live
    -0.25
    POSITIVE LOGITS
    foreach
    0.96
    string
    0.83
     foreach
    0.80
     Италијани
    0.78
     string
    0.77
    parsedMessage
    0.76
     surla
    0.76
    mybatisplus
    0.75
    var
    0.74
     تضيفلها
    0.71
    Activations Density 0.088%

    No Known Activations