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. 851
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and special characters

    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
    ientí
    -0.83
    atimes
    -0.75
    witzerland
    -0.71
    dalena
    -0.70
    PageRoute
    -0.70
    amemnon
    -0.70
    jsonwebtoken
    -0.69
     CURLOPT
    -0.68
    $_['
    -0.68
     itself
    -0.67
    POSITIVE LOGITS
    -
    1.05
    ‐
    0.66
     directora
    0.61
     née
    0.55
    ‑
    0.54
    she
    0.53
    MigrationBuilder
    0.50
    ־
    0.48
    Numerology
    0.46
     nee
    0.45
    Activations Density 0.376%

    No Known Activations