© 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. 21-GEMMASCOPE-RES-16K
    11. 10925
    Prev
    Next
    INDEX
    Explanations

    technical processes and evaluations related to data, analysis, and experimentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.40
    chuan
    -0.35
    Données
    -0.35
    testens
    -0.34
    duga
    -0.34
     Architekt
    -0.33
    mez
    -0.33
    %%
    -0.33
    moduleId
    -0.33
    ecé
    -0.32
    POSITIVE LOGITS
    RenderAtEndOf
    1.00
     afterward
    0.64
    GOTREF
    0.62
    UseVisualStyle
    0.61
    Datuak
    0.59
    principalColumn
    0.59
    Демографія
    0.58
    ScopeManager
    0.58
    TypedDataSet
    0.58
    setVerticalGroup
    0.54
    Activations Density 0.910%

    No Known Activations