© 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
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3027
    Prev
    Next
    INDEX
    Explanations

    terms and references related to legal and medical contexts, specifically focusing on cases and procedural aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __).
    -0.57
    MergeFrom
    -0.56
    )».
    -0.55
     nabíz
    -0.54
     indígen
    -0.54
     poichè
    -0.52
    DockStyle
    -0.52
    CloseOperation
    -0.52
    InSection
    -0.51
     }{@
    -0.50
    POSITIVE LOGITS
     teeth
    0.34
     phone
    0.34
    .
    0.34
     sạn
    0.33
    ereien
    0.33
     operation
    0.32
    cetto
    0.32
     beds
    0.32
    CHREIB
    0.32
     حال
    0.31
    Activations Density 3.186%

    No Known Activations