Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 110801
    Prev
    Next
    INDEX
    Explanations

    terms related to sculpture and sculptural forms

    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
     Max
    -0.48
    Max
    -0.46
    addFlags
    -0.46
     Allgemeine
    -0.46
    posedge
    -0.45
    Willy
    -0.45
     Nex
    -0.44
     wrong
    -0.44
    Bree
    -0.44
    ckeye
    -0.43
    POSITIVE LOGITS
     sculpture
    1.27
    sculpture
    1.17
    Sculpture
    1.16
     Sculpture
    1.13
     sculptures
    1.08
     escultura
    1.02
     sculpting
    0.94
     sculpt
    0.93
     Scul
    0.91
    scul
    0.89
    Activations Density 0.003%

    No Known Activations