© 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. 9-GEMMASCOPE-RES-16K
    11. 14926
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes related to layout and navigation

    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
     ModelExpression
    -0.85
    principalColumn
    -0.83
    GraphicsUnit
    -0.73
    ThroughAttribute
    -0.73
    fjspx
    -0.66
    ScopeManager
    -0.64
    posedge
    -0.64
    principalTable
    -0.62
     AspNetCore
    -0.62
    formik
    -0.60
    POSITIVE LOGITS
     lyre
    0.69
     بيها
    0.66
     negroes
    0.62
     espagne
    0.60
     purpoſe
    0.59
     pleaſure
    0.58
     enquiry
    0.58
     getContent
    0.57
     Plin
    0.56
     Lepto
    0.56
    Activations Density 0.141%

    No Known Activations