© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    terms related to secrecy and secretive organizations

    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
    MigrationBuilder
    -0.75
    DeleteBehavior
    -0.69
     estekak
    -0.67
     mxArray
    -0.66
     Vivaldi
    -0.63
     مرئيه
    -0.60
    хьтан
    -0.59
    harusnya
    -0.59
     pinulongan
    -0.58
    houses
    -0.57
    POSITIVE LOGITS
     Sec
    0.88
     sec
    0.75
    Sec
    0.73
     SECRET
    0.71
     SEC
    0.70
    seca
    0.68
     secr
    0.66
     Secret
    0.65
    Secs
    0.62
    Secret
    0.59
    Activations Density 0.205%

    No Known Activations