© 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. 21-GEMMASCOPE-RES-16K
    11. 13152
    Prev
    Next
    INDEX
    Explanations

    negations or phrases expressing what something is not

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     chi̍t
    -0.91
    setVerticalGroup
    -0.79
     Vikipedi
    -0.76
    AutoScaleMode
    -0.76
     ModelExpression
    -0.75
     lenker
    -0.73
    RenderAtEndOf
    -0.70
     Administrativna
    -0.69
     intptr
    -0.69
    TestBed
    -0.68
    POSITIVE LOGITS
     uncommon
    0.69
     even
    0.63
     fair
    0.62
     meant
    0.61
     supposed
    0.61
     intended
    0.57
     gonna
    0.56
     something
    0.55
     going
    0.53
     unusual
    0.52
    Activations Density 0.217%

    No Known Activations