© 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. 0-GEMMASCOPE-RES-16K
    6. 8158
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers associated with people or objects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GB
    -0.40
    懸命
    -0.38
     Ri
    -0.36
    Gal
    -0.36
     Gal
    -0.35
    nico
    -0.35
    rr
    -0.35
    gal
    -0.34
    toThrow
    -0.34
    ch
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.81
     fortune
    0.81
    RenderAtEndOf
    0.80
     ModelExpression
    0.75
     increí
    0.70
     snippetHide
    0.70
    Fortune
    0.69
     Fortune
    0.67
     marshal
    0.67
    <unused52>
    0.66
    Activations Density 0.209%

    No Known Activations