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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3362
    Prev
    Next
    INDEX
    Explanations

    header files and script tags in code

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MessageOf
    -0.60
    httphttps
    -0.59
    webtoken
    -0.53
     Taktlose
    -0.51
    GeneratedMessage
    -0.50
     Chwiliwch
    -0.49
    ğraf
    -0.47
     Савезне
    -0.47
    jsonwebtoken
    -0.46
     <>",
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.63
     girasol
    0.44
    脚注の使い方
    0.42
    ViewImports
    0.40
    AutoField
    0.39
    +#+#
    0.38
    visející
    0.36
    GTCX
    0.36
    CppMethod
    0.35
     Szene
    0.35
    Activations Density 0.143%

    No Known Activations