© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8223
    Prev
    Next
    INDEX
    Explanations

    comparative phrases describing medication efficacy and side effects

    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
    المناصب
    -0.70
    bootstrapcdn
    -0.60
    ędziesz
    -0.58
    mybatisplus
    -0.56
    styleable
    -0.56
    endphp
    -0.55
    adpleegd
    -0.54
    RenderAtEndOf
    -0.54
    CreateMap
    -0.52
    WritableDatabase
    -0.50
    POSITIVE LOGITS
     minor
    2.17
     small
    2.16
     tiny
    2.10
     insignificant
    1.99
    small
    1.91
    minor
    1.83
    tiny
    1.79
    Small
    1.77
     SMALL
    1.71
    Minor
    1.70
    Activations Density 0.905%

    No Known Activations