© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15844
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to evaluation and assessment

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

    great deeds, main features, run website, out bandwidth, believes Android, composition of

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     itself
    -0.38
    .
    -0.37
    ;
    -0.34
    H
    -0.32
    M
    -0.32
    ,
    -0.31
    O
    -0.31
    3
    -0.31
    V
    -0.31
    A
    -0.30
    POSITIVE LOGITS
    <unused41>
    1.22
    <unused3>
    1.21
    <unused16>
    1.21
    <unused42>
    1.21
    <unused52>
    1.21
    [@BOS@]
    1.21
    <unused8>
    1.21
    <unused28>
    1.21
    <unused74>
    1.21
    <unused17>
    1.21
    Activations Density 0.018%

    No Known Activations