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. 30
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" and other significant personal identifiers or elements in 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
     للمعارف
    -0.83
    UnsafeEnabled
    -0.78
     تانيه
    -0.76
    posedge
    -0.75
     ModelExpression
    -0.75
     AssemblyTitle
    -0.74
    rawDesc
    -0.73
    didSet
    -0.72
    webElementXpaths
    -0.70
     saites
    -0.70
    POSITIVE LOGITS
    cob
    0.49
    <eos>
    0.47
     tongs
    0.45
    DMC
    0.43
     DMC
    0.42
    AllowUser
    0.41
    Block
    0.41
    vida
    0.40
     Braun
    0.40
     urchin
    0.39
    Activations Density 0.000%

    No Known Activations