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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 8349
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "const" and its variations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.67
     AppCompatTheme
    -0.64
     bezeichneter
    -0.58
    DeleteBehavior
    -0.57
    انيف
    -0.56
     propOrder
    -0.56
    -------
    -0.55
    spl
    -0.54
    MigrationBuilder
    -0.53
    sequelize
    -0.52
    POSITIVE LOGITS
    const
    0.88
     const
    0.86
     Himo
    0.57
    '||
    0.57
     ProtoMessage
    0.57
    gens
    0.56
     puis
    0.54
    enumi
    0.54
    licky
    0.54
     Ressource
    0.53
    Activations Density 0.103%

    No Known Activations