© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13797
    Prev
    Next
    INDEX
    Explanations

    bold formatting in the text

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

    HTML bold tag

    np_acts-logits-general · gemini-2.0-flash

    appearance, schedule, night, pack, date, break, app, display

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Gatt
    -0.50
    </strong>
    -0.47
     Châte
    -0.46
    tale
    -0.45
     Hyp
    -0.45
    Tale
    -0.45
     promesa
    -0.45
     Verg
    -0.44
     Palt
    -0.44
    <strong>
    -0.44
    POSITIVE LOGITS
    <b>
    0.71
    </b>
    0.59
    /*
    0.57
     eventId
    0.53
     {\
    0.53
     ${\
    0.52
     AssemblyTitle
    0.52
    例文帳に追加
    0.51
    ly
    0.51
    basicConfig
    0.50
    Activations Density 0.156%

    No Known Activations