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. 419
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to engineering or mechanical designs

    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
     présidentielle
    -0.65
    expandindo
    -0.64
    rungsseite
    -0.63
    KommentareTeilen
    -0.60
    StartTag
    -0.58
    MongoClient
    -0.58
    UnusedPrivate
    -0.58
     Wilber
    -0.58
     bolí
    -0.58
    scriptcase
    -0.58
    POSITIVE LOGITS
    iece
    0.59
    asties
    0.58
    designs
    0.57
     designs
    0.57
     Designs
    0.56
    setVerticalGroup
    0.56
    details
    0.53
     Desain
    0.52
    BOND
    0.52
    \}\
    0.51
    Activations Density 0.001%

    No Known Activations