© 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. 4-GEMMASCOPE-RES-16K
    11. 865
    Prev
    Next
    INDEX
    Explanations

    terms related to collective behavior and group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.53
    papers
    -0.45
    endphp
    -0.45
     ExecuteAsync
    -0.45
     Réponses
    -0.45
    }`;
    -0.44
    нечно
    -0.44
    앵
    -0.44
    iação
    -0.44
    //
    -0.43
    POSITIVE LOGITS
     collective
    1.20
     colectiva
    1.10
     collectively
    1.02
     collectif
    1.02
    collective
    0.98
     Collective
    0.95
    Collective
    0.93
    集体
    0.92
     kollek
    0.87
     colectivo
    0.83
    Activations Density 1.044%

    No Known Activations