© 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. 8985
    Prev
    Next
    INDEX
    Explanations

    mentions of representation and its impact on diversity and equity

    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
    ScopeManager
    -0.78
     ſeveral
    -0.76
     beſt
    -0.72
    AutoField
    -0.72
    protoimpl
    -0.70
    !("{}",
    -0.69
     <=",
    -0.68
    первых
    -0.68
    GEBURTSDATUM
    -0.68
     laſt
    -0.68
    POSITIVE LOGITS
     others
    1.03
    Others
    0.99
    others
    0.97
     Others
    0.92
     OTHERS
    0.86
     остальных
    0.82
     остальные
    0.79
    其他人
    0.74
     other
    0.71
     enquanto
    0.68
    Activations Density 0.695%

    No Known Activations