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. 50
    Prev
    Next
    INDEX
    Explanations

    URLs or web links in the text

    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
     betweenstory
    -0.69
    ungkinan
    -0.61
    StructEnd
    -0.56
    IndentedString
    -0.52
    BackPressed
    -0.52
    CppMethod
    -0.51
     censiti
    -0.50
    exitRule
    -0.49
    ThroughAttribute
    -0.49
    vident
    -0.48
    POSITIVE LOGITS
    NewLabel
    0.60
     Waray
    0.59
    рец
    0.59
    vatar
    0.58
     Jaffe
    0.57
    othes
    0.55
     חיצוניים
    0.55
    .*")]
    0.54
    ownic
    0.54
    전히
    0.53
    Activations Density 0.006%

    No Known Activations