© 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. 9-GEMMASCOPE-RES-16K
    6. 2462
    Prev
    Next
    INDEX
    Explanations

    specific mentions of brands or companies, particularly in the context of products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guin
    -1.00
    qin
    -1.00
     Echin
    -0.93
    tin
    -0.91
    Tin
    -0.88
    nestjs
    -0.87
    in
    -0.87
    NameInMap
    -0.86
    IN
    -0.86
    rin
    -0.84
    POSITIVE LOGITS
     Keyes
    0.78
    Pathway
    0.76
     Gibbons
    0.75
     Andorra
    0.73
     tertawa
    0.72
     Jon
    0.72
     Clive
    0.72
    feldt
    0.71
    ціє
    0.71
    scriber
    0.71
    Activations Density 1.153%

    No Known Activations