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. 51937
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in text

    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
     Meksiku
    -0.45
     Савезне
    -0.44
    //
    -0.43
    Frust
    -0.43
    ɬ
    -0.41
    contentLoaded
    -0.41
    Human
    -0.40
     Ironically
    -0.39
     otomatig
    -0.39
    UCLA
    -0.39
    POSITIVE LOGITS
    WriteTagHelper
    0.64
    TagMode
    0.56
    QMetaType
    0.55
    AddTagHelper
    0.52
    tagHelperRunner
    0.48
    ftagPool
    0.47
     समीक्षाओं
    0.45
    ording
    0.43
     ModelExpression
    0.42
    AndEndTag
    0.42
    Activations Density 0.037%

    No Known Activations