© 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. 12-GEMMASCOPE-RES-16K
    6. 3807
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to biological and cellular concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    titleMargin
    -0.47
    outSlope
    -0.46
     विश्वसनीयता
    -0.45
    แส
    -0.40
    MigrationBuilder
    -0.39
     Folgen
    -0.38
     Darauf
    -0.38
    rewind
    -0.37
     thèmes
    -0.37
    testify
    -0.37
    POSITIVE LOGITS
    matchCondition
    0.59
    StoreMessageInfo
    0.58
    лтемелер
    0.53
    تقاوى
    0.49
    mybatisplus
    0.48
    WithIOException
    0.48
    Дереккөздер
    0.48
    帖最后由
    0.46
    httphttps
    0.43
     createState
    0.43
    Activations Density 10.420%

    No Known Activations