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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73519
    Prev
    Next
    INDEX
    Explanations

    numerical values or expressions related to colors and styles in CSS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.71
    abestanden
    -0.68
    الدراسه
    -0.67
    ]")]
    -0.66
    новништво
    -0.63
    findpost
    -0.63
    帖最后由
    -0.60
     nakalista
    -0.58
     zuſammen
    -0.58
     deſſen
    -0.58
    POSITIVE LOGITS
    full
    0.38
     prioridad
    0.33
    ksanakan
    0.33
     diversidad
    0.32
     hvorfor
    0.32
     høy
    0.32
     fraî
    0.31
    üme
    0.31
     Masalah
    0.31
    priority
    0.30
    Activations Density 0.001%

    No Known Activations