© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7487
    Prev
    Next
    INDEX
    Explanations

    references to roles and influences within scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.48
     atend
    -0.46
     доволь
    -0.45
    аль
    -0.45
     cima
    -0.43
     Routed
    -0.43
     esbo
    -0.42
    zec
    -0.42
    素
    -0.41
     umum
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.89
     role
    0.86
     влияние
    0.84
     Role
    0.80
    Role
    0.78
    fulness
    0.75
     impact
    0.74
    Portály
    0.74
     ROLE
    0.72
    ROLE
    0.72
    Activations Density 0.503%

    No Known Activations