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. 510
    Prev
    Next
    INDEX
    Explanations

    actions related to burial or entombment

    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
    WithIOException
    -0.81
     >=",
    -0.58
    rouille
    -0.55
    зія
    -0.54
    CMV
    -0.53
    taminophen
    -0.51
    oleic
    -0.50
     opinion
    -0.50
     Opinion
    -0.49
    reactivex
    -0.48
    POSITIVE LOGITS
    MLLoader
    0.67
    ANSA
    0.57
    jspx
    0.56
    Clik
    0.55
    PMailer
    0.54
    UpInside
    0.54
     Driscoll
    0.53
    Kariera
    0.52
     vendita
    0.51
     dimas
    0.50
    Activations Density 0.005%

    No Known Activations