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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9673
    Prev
    Next
    INDEX
    Explanations

    specific data structures and coding syntax elements within programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.81
    :✨
    -0.79
    Personendaten
    -0.78
    __*/
    -0.78
    SourceChecksum
    -0.78
    DropColumn
    -0.76
    IVEREF
    -0.75
    UrlResolution
    -0.75
    principalColumn
    -0.73
    DropTable
    -0.72
    POSITIVE LOGITS
     vindo
    0.53
    woordig
    0.52
     hakkında
    0.48
     Angleterre
    0.45
    rous
    0.44
     Queste
    0.44
     cykel
    0.43
    isalpha
    0.43
    Submitted
    0.41
    PYX
    0.41
    Activations Density 0.577%

    No Known Activations