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. 131
    Prev
    Next
    INDEX
    Explanations

    references to publishing houses

    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
    assium
    -0.66
     Promise
    -0.66
     Dhan
    -0.65
    getColumnIndex
    -0.65
     تانيه
    -0.64
    __(/*!
    -0.63
    ENCOD
    -0.61
     Boh
    -0.60
     Chon
    -0.59
     beden
    -0.59
    POSITIVE LOGITS
    Verlag
    2.06
    verlag
    0.81
     Verlag
    0.75
    Abitanti
    0.59
    Спољашње
    0.57
    thansa
    0.57
    CrossRef
    0.56
    낌
    0.56
    PreferredItem
    0.52
     Verses
    0.52
    Activations Density 0.000%

    No Known Activations