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. 507
    Prev
    Next
    INDEX
    Explanations

    terms related to textiles and fabric

    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
    principalTable
    -0.80
    ta
    -0.73
    та
    -0.66
    i
    -0.65
    <strong>
    -0.64
    en
    -0.64
     diarias
    -0.63
     actie
    -0.62
    y
    -0.62
    na
    -0.61
    POSITIVE LOGITS
     heirloom
    1.50
    loom
    1.18
    leſs
    1.16
     $_"
    1.14
    ſelf
    1.10
     Heir
    1.09
     doubtnut
    1.07
     ſeveral
    1.07
     ―――――
    1.07
     itſelf
    1.05
    Activations Density 0.000%

    No Known Activations