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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38759
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions or assessments of value and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     actos
    -0.36
     endlessly
    -0.35
     беско
    -0.34
     transparence
    -0.34
     eternally
    -0.34
     prohibido
    -0.34
     polega
    -0.32
    GeneratedValue
    -0.32
     vengan
    -0.31
     endless
    -0.31
    POSITIVE LOGITS
     sizable
    1.02
     sizeable
    0.94
     Considerable
    0.85
     considerable
    0.83
     substantial
    0.82
    Decent
    0.82
     decent
    0.81
     Substantial
    0.81
    considerable
    0.80
    sizable
    0.79
    Activations Density 0.037%

    No Known Activations