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. 13573
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    minecraftforge
    -0.50
    Ro
    -0.46
    hasMoreElements
    -0.45
    MathML
    -0.44
    Grade
    -0.44
    Handle
    -0.44
     arg
    -0.43
     moh
    -0.43
    Scroll
    -0.43
    <?
    
    -0.43
    POSITIVE LOGITS
    AnchorStyles
    0.73
    SerializedSize
    0.70
     connexes
    0.63
    RectangleBorder
    0.60
    ConstraintMaker
    0.60
     doInBackground
    0.59
    extAlignment
    0.57
    createTextNode
    0.57
    onViewCreated
    0.57
    XmlAccessType
    0.56
    Activations Density 0.194%

    No Known Activations