© 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. 17-GEMMASCOPE-RES-16K
    11. 11197
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or classifications of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.92
     Monfieur
    -0.80
     Efq
    -0.79
    ecap
    -0.76
     Fascism
    -0.75
     faſt
    -0.69
     itſelf
    -0.69
     oreilles
    -0.66
    ChildScrollView
    -0.66
     cleft
    -0.65
    POSITIVE LOGITS
     who
    1.16
     whom
    0.77
     whose
    0.76
    时候
    0.72
    Whose
    0.66
     pesky
    0.65
    ScopeManager
    0.65
    genen
    0.63
     Folks
    0.62
    ionados
    0.62
    Activations Density 0.071%

    No Known Activations