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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 8782
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and discussions

    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
    ViewImports
    -0.68
    hoeddwyd
    -0.66
    endphp
    -0.58
     Meksiku
    -0.56
     الحره
    -0.55
    endpush
    -0.55
     Roskov
    -0.54
    OGND
    -0.53
     poros
    -0.53
    蚪
    -0.53
    POSITIVE LOGITS
    Elementos
    0.35
     advertencia
    0.34
     zasad
    0.34
    apimachinery
    0.34
     jembatan
    0.33
     suceder
    0.33
    évaluation
    0.32
     taşı
    0.32
     importância
    0.32
     accomplish
    0.31
    Activations Density 0.076%

    No Known Activations