© 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. 10758
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming and data structure definitions

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

    case statements in switch blocks that handle protocol buffer field decoding.

    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
    parsedMessage
    -0.49
    
    -0.48
    rrggbb
    -0.45
    transQ
    -0.41
    Vidite
    -0.41
    WebElementEntity
    -0.41
     gekomen
    -0.41
     defStyle
    -0.40
     duquel
    -0.38
     Vergangenheit
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.74
    帖最后由
    0.59
    withstanding
    0.57
     noDo
    0.56
     الحره
    0.54
    页面存档备份
    0.54
    Diwedd
    0.51
    RectangleBorder
    0.51
    RenderAtEndOf
    0.50
     kle
    0.49
    Activations Density 0.354%

    No Known Activations