© 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. 15-GEMMASCOPE-RES-16K
    11. 5300
    Prev
    Next
    INDEX
    Explanations

    terms associated with market opportunities and projections for industry growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    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
    -0.66
     kohta
    -0.52
     amanhã
    -0.52
    jalá
    -0.51
    IsMutable
    -0.51
    DropColumn
    -0.48
    JsonPropertyName
    -0.48
     myö
    -0.48
     heretics
    -0.48
     materie
    -0.47
    POSITIVE LOGITS
    jsdelivr
    0.73
    bootstrapcdn
    0.64
     demand
    0.64
     препратки
    0.63
     bouche
    0.59
     appeal
    0.59
     incentives
    0.59
     increased
    0.59
     popular
    0.58
    writeFieldEnd
    0.58
    Activations Density 0.251%

    No Known Activations