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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99774
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and their numbering or identifiers

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

    legal citations

    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
    Personensuche
    -0.83
    contentLoaded
    -0.72
    tagHelperRunner
    -0.69
    Diweddarwch
    -0.66
     ddelwed
    -0.65
    IntoConstraints
    -0.65
     picioare
    -0.63
    <unused41>
    -0.63
    <unused16>
    -0.63
    <unused8>
    -0.63
    POSITIVE LOGITS
    Flag
    0.32
    ※
    0.31
    Infof
    0.31
    March
    0.30
        
    0.30
    SH
    0.30
    Reminder
    0.29
    DIV
    0.29
     Hoffnung
    0.29
    IK
    0.29
    Activations Density 0.165%

    No Known Activations