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. 1067
    Prev
    Next
    INDEX
    Explanations

    references to chemical elements and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chemical elements and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     disambiguazione
    -0.58
    endpush
    -0.49
     يتيمه
    -0.48
     Roskov
    -0.45
    ngdoc
    -0.45
     EconPapers
    -0.44
     <=",
    -0.43
    ✭✭
    -0.42
    NameInMap
    -0.41
     kaarangay
    -0.41
    POSITIVE LOGITS
    LabelTagHelper
    0.50
     actionMode
    0.49
    aarrggbb
    0.44
     plastik
    0.44
    Economy
    0.42
    Plastic
    0.42
     Plastic
    0.42
    NSE
    0.42
     HDPE
    0.42
     MPI
    0.41
    Activations Density 0.258%

    No Known Activations