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. 43326
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured data or programming elements that signify the initiation of concepts or commands

    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
     '
    -0.52
    <eos>
    -0.50
     min
    -0.49
     N
    -0.47
     
    -0.45
     ю
    -0.45
    пас
    -0.44
     Y
    -0.44
    ifter
    -0.44
     rov
    -0.43
    POSITIVE LOGITS
     ModelExpression
    10.31
     CreateTagHelper
    1.80
     AspNetCore
    1.66
    ConstraintMaker
    1.62
    findpost
    1.61
    
    1.61
    GEBURTSDATUM
    1.55
    ContentAsync
    1.55
     كومونز
    1.48
    AndEndTag
    1.48
    Activations Density 0.001%

    No Known Activations