Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 122322
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating significant events or roles in narratives

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

    trade, major, rights, outrage, sewer

    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
    abcdefghijklmnop
    -0.26
     esclavos
    -0.24
     specific
    -0.24
     slik
    -0.24
     élastique
    -0.23
     Gegend
    -0.23
    specific
    -0.23
     natuur
    -0.23
     صفحۀ
    -0.22
    Bibliograf
    -0.22
    POSITIVE LOGITS
     fashiola
    0.95
     zwiſchen
    0.94
    <unused68>
    0.93
    <unused74>
    0.93
    <unused41>
    0.93
    [@BOS@]
    0.93
    <unused28>
    0.93
    <unused42>
    0.93
    <unused14>
    0.93
    <unused8>
    0.93
    Activations Density 0.052%

    No Known Activations