© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10027
    Prev
    Next
    INDEX
    Explanations

    details related to analysis and categorization of various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.63
    migrationBuilder
    -0.60
    contentLoaded
    -0.53
    Hochspringen
    -0.50
    yntaxException
    -0.47
    üge
    -0.46
     mijne
    -0.46
    MigrationBuilder
    -0.46
    pecabe
    -0.45
    
    -0.45
    POSITIVE LOGITS
     subsidiary
    1.88
     sub
    1.78
     secondary
    1.63
     ancillary
    1.51
     auxiliary
    1.44
     subordinate
    1.41
     subsidiaries
    1.34
    sub
    1.32
    secondary
    1.29
    サブ
    1.28
    Activations Density 1.648%

    No Known Activations