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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 108438
    Prev
    Next
    INDEX
    Explanations

    references to analysis and evaluation of strategies and actions

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

    positive outcomes

    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
     propOrder
    -0.86
    BufferException
    -0.66
    MigrationBuilder
    -0.60
    tagHelperRunner
    -0.57
     كومونز
    -0.56
    aarrggbb
    -0.55
    httphttps
    -0.53
    ſelf
    -0.53
     nakalista
    -0.53
    ViewImports
    -0.52
    POSITIVE LOGITS
     mercad
    0.46
     Numerade
    0.46
     financeira
    0.45
     nyky
    0.44
     fakty
    0.43
     muerta
    0.43
     ganda
    0.42
     badan
    0.42
    จัก
    0.42
     Zelanda
    0.42
    Activations Density 0.180%

    No Known Activations