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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6931
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.38
     صباح
    -0.37
     sabah
    -0.36
    BSITE
    -0.35
     ramo
    -0.34
    Breakfast
    -0.34
    tralight
    -0.34
     breakfasts
    -0.34
    الدراسه
    -0.34
    beforeEach
    -0.34
    POSITIVE LOGITS
    ท้าย
    0.66
     FINAL
    0.60
     akhir
    0.59
     finale
    0.58
     Final
    0.58
     autorytatywna
    0.57
    footer
    0.56
    Final
    0.56
     final
    0.56
    Finale
    0.54
    Activations Density 0.648%

    No Known Activations