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. 6
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe a quality or state

    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
    Datuak
    -1.20
     виправивши
    -1.07
    +#+#
    -1.05
    WriteLiteral
    -0.97
    parsedMessage
    -0.90
    InSection
    -0.89
    RectangleBorder
    -0.88
    crollView
    -0.82
     initComponents
    -0.81
     XCTest
    -0.81
    POSITIVE LOGITS
     Manly
    1.67
     Manley
    1.06
     manly
    1.04
     man
    0.86
     Man
    0.80
     MAN
    0.79
    man
    0.77
     Dandy
    0.75
    Manny
    0.74
     Mancini
    0.72
    Activations Density 0.000%

    No Known Activations