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 - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 7589
    Prev
    Next
    INDEX
    Explanations

    assertions and references related to entitlement or claims of ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.64
     communiquez
    -0.59
     cosa
    -0.58
    Jegyzetek
    -0.57
    קישורים
    -0.55
    ecznie
    -0.54
    Personensuche
    -0.54
     integrante
    -0.53
     Италијани
    -0.53
     GUYS
    -0.53
    POSITIVE LOGITS
    makeText
    0.67
    CommandText
    0.63
     own
    0.60
    IBOutlet
    0.59
    PMailer
    0.58
    rrggbb
    0.56
    AddAttribute
    0.56
     Maker
    0.56
    KeySpec
    0.55
     relations
    0.54
    Activations Density 0.391%

    No Known Activations