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. 13-GEMMASCOPE-RES-16K
    6. 15416
    Prev
    Next
    INDEX
    Explanations

    comments and documentation related to functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.78
    MessageOf
    -0.70
    parsedMessage
    -0.67
    oredCriteria
    -0.63
    رشف
    -0.61
    basicConfig
    -0.56
    ://$
    -0.55
    awtextra
    -0.52
    autorelease
    -0.52
     ProtoMessage
    -0.51
    POSITIVE LOGITS
    Fungsi
    0.61
     avviene
    0.59
     functor
    0.56
    abestanden
    0.56
     procédure
    0.55
     Chwiliwch
    0.55
     Pilate
    0.55
     functie
    0.54
     Cæsar
    0.52
     effettuare
    0.51
    Activations Density 0.157%

    No Known Activations