© 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. 16211
    Prev
    Next
    INDEX
    Explanations

    key details and elements related to plans, events, and announcements

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

    reports presented or analyzed

    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
     ...
    -0.36
     (
    -0.33
    ...
    -0.31
     still
    -0.30
     individual
    -0.29
     …
    -0.29
     Universitaria
    -0.27
     restricciones
    -0.27
     latter
    -0.27
    With
    -0.26
    POSITIVE LOGITS
    expandindo
    0.97
    RenderAtEndOf
    0.94
    ſchaft
    0.91
     zwiſchen
    0.88
    <unused8>
    0.88
    [@BOS@]
    0.88
    <unused23>
    0.88
    <unused79>
    0.88
    <pad>
    0.87
    <unused14>
    0.87
    Activations Density 0.133%

    No Known Activations