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 Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13556
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations, particularly parentheses and expressions related to derivatives or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Ersten
    -0.66
     A
    -0.57
     I
    -0.57
     H
    -0.56
     C
    -0.54
     B
    -0.52
    ,
    -0.52
    !
    -0.52
     The
    -0.49
     can
    -0.47
    POSITIVE LOGITS
    kháu
    1.20
    MigrationBuilder
    1.19
    :✨
    1.17
    aarrggbb
    1.13
     betweenstory
    1.09
     disponibilités
    1.08
    parsedMessage
    1.07
     otomatig
    1.04
    uxxxx
    1.02
     <=",
    1.01
    Activations Density 0.497%

    No Known Activations