© 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. 4469
    Prev
    Next
    INDEX
    Explanations

    code segments related to application error handling and logging

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

    whitespace and indentation at the beginning of lines in code.

    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
     pstmt
    -0.79
     GoogleFonts
    -0.72
    ſelf
    -0.70
    HandlerContext
    -0.68
     ſes
    -0.65
     getState
    -0.64
     lateinit
    -0.64
     recyclerView
    -0.64
     currentState
    -0.63
    сылкі
    -0.63
    POSITIVE LOGITS
    if
    0.68
    switch
    0.49
     if
    0.44
    for
    0.44
    while
    0.43
     ikiwa
    0.40
    //
    0.36
    I
    0.35
    try
    0.35
    According
    0.33
    Activations Density 0.279%

    No Known Activations