© 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. 16-GEMMASCOPE-RES-16K
    11. 5446
    Prev
    Next
    INDEX
    Explanations

    specific references to legal cases, entities, and formal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding a person or institution

    np_acts-logits-general · gemini-2.0-flash

    academic and research contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     célèbres
    -0.68
     connue
    -0.61
     respectivement
    -0.58
     pulito
    -0.56
     connues
    -0.56
     connus
    -0.55
     partea
    -0.53
     accompagné
    -0.52
     épu
    -0.52
     attiva
    -0.52
    POSITIVE LOGITS
    NUMX
    0.77
    [])
    0.76
    ThroughAttribute
    0.75
    Архівовано
    0.74
    __":
    0.72
    elemField
    0.70
    rawDesc
    0.68
    InjectAttribute
    0.68
    flashdata
    0.66
     Taktlose
    0.66
    Activations Density 0.719%

    No Known Activations