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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 38913
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming data types and their characteristics

    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
    netbeans
    -0.40
    MethodManager
    -0.38
    #+#
    -0.38
     cru
    -0.36
     siguiente
    -0.35
     follow
    -0.35
     peric
    -0.35
     camped
    -0.34
    oneg
    -0.34
    håll
    -0.34
    POSITIVE LOGITS
    MigrationBuilder
    0.64
     సౌకర్య
    0.57
     transfieras
    0.56
     marinho
    0.47
     Waray
    0.45
    millimeters
    0.44
     olympique
    0.43
     Europy
    0.42
     cioè
    0.41
    普及
    0.41
    Activations Density 0.087%

    No Known Activations