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. 21-GEMMASCOPE-RES-16K
    6. 2838
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.83
    berdayakan
    -0.82
    orneys
    -0.80
    muerzo
    -0.75
     déchir
    -0.73
     nahilalakip
    -0.72
    GraphicsUnit
    -0.72
    ResumeLayout
    -0.68
    Климат
    -0.68
     fidé
    -0.67
    POSITIVE LOGITS
    Nowadays
    1.05
    Apart
    1.04
     Nowadays
    1.01
     Apart
    0.99
    Moreover
    0.97
     Moreover
    0.95
     Besides
    0.90
    Besides
    0.89
     beside
    0.88
     Beside
    0.86
    Activations Density 0.339%

    No Known Activations