Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16178
    Prev
    Next
    INDEX
    Explanations

    references to assets and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colha
    -0.81
    racuse
    -0.81
    UMNS
    -0.81
    ukone
    -0.79
     referenties
    -0.78
    Demografía
    -0.77
    MigrationBuilder
    -0.76
    endphp
    -0.76
    istice
    -0.76
    untura
    -0.75
    POSITIVE LOGITS
     Assets
    1.01
     assets
    0.98
    ConstraintMaker
    0.87
    ASSET
    0.84
     asset
    0.83
     ASSETS
    0.82
     Asset
    0.82
    Assets
    0.81
     asse
    0.73
     hips
    0.71
    Activations Density 0.129%

    No Known Activations