© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 3250
    Prev
    Next
    INDEX
    Explanations

    names and references related to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIdentifier
    -0.42
    공
    -0.38
    تقاوى
    -0.37
    isand
    -0.37
    IsMutable
    -0.36
     interfer
    -0.35
     fossa
    -0.34
    守
    -0.33
     perfor
    -0.33
     temper
    -0.33
    POSITIVE LOGITS
    AsUp
    0.56
    RenderAtEndOf
    0.54
    发表于
    0.51
     ब्रेकडाउन
    0.50
     Wicidata
    0.50
    +#+
    0.49
     ModelExpression
    0.49
     dalamnya
    0.49
    ########.
    0.48
     regno
    0.47
    Activations Density 1.116%

    No Known Activations