© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16388
    Prev
    Next
    INDEX
    Explanations

    specific terms and values related to mathematical calculations and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    split
    -0.31
     “
    -0.30
     pag
    -0.29
    ٔ
    -0.29
     f
    -0.28
     
    -0.27
     pi
    -0.27
     v
    -0.27
    =”
    -0.27
    ;++
    -0.27
    POSITIVE LOGITS
    parsedMessage
    0.94
     ब्रेकडाउन
    0.83
    expandindo
    0.80
     ProtoMessage
    0.73
    ⤹
    0.69
     desmotivaciones
    0.68
     Италијани
    0.66
    matchCondition
    0.65
    <unused16>
    0.65
    <unused3>
    0.65
    Activations Density 0.322%

    No Known Activations