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. 0-GEMMASCOPE-RES-16K
    6. 7829
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.83
    MigrationBuilder
    -1.79
     myſelf
    -1.77
     ſind
    -1.75
     itſelf
    -1.74
    Datuak
    -1.74
     Савезне
    -1.70
     photolibrary
    -1.69
    ^(@)
    -1.68
    Personensuche
    -1.67
    POSITIVE LOGITS
     the
    1.20
     
    1.11
     a
    1.07
    ,
    1.00
    ↵↵
    0.97
     to
    0.97
     for
    0.96
     in
    0.96
     (
    0.91
     I
    0.91
    Activations Density 5.533%

    No Known Activations