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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 74
    Prev
    Next
    INDEX
    Explanations

    references to durations of time, especially those related to imprisonment or captivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
     disambiguazione
    -0.98
     surla
    -0.95
     &___
    -0.88
     ExecuteAsync
    -0.77
    migrationBuilder
    -0.76
     AssemblyCulture
    -0.75
    tagext
    -0.74
    SequentialGroup
    -0.73
    providedIn
    -0.67
     <=",
    -0.67
    POSITIVE LOGITS
     identificação
    0.46
     debating
    0.46
     campaigned
    0.45
    خر
    0.44
     вікі
    0.43
     capito
    0.43
    Knows
    0.43
     encephalitis
    0.43
     meningitis
    0.43
    нциклопедия
    0.42
    Activations Density 0.002%

    No Known Activations