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. 8837
    Prev
    Next
    INDEX
    Explanations

    instances of backslashes and underscores in the text

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

    software, ORM, handlers, bindings

    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
     fall
    -0.37
     szok
    -0.36
     SUBST
    -0.34
     raisonnable
    -0.34
     ending
    -0.33
    序
    -0.33
     during
    -0.33
     even
    -0.32
     ROT
    -0.32
     after
    -0.32
    POSITIVE LOGITS
     المعيارى
    0.93
    parsedMessage
    0.74
    MessageTagHelper
    0.71
    ViewImports
    0.71
     виправивши
    0.70
     للمعارف
    0.69
     الرياضيه
    0.67
    OGND
    0.66
    ThroughAttribute
    0.66
    IsMutable
    0.65
    Activations Density 0.009%

    No Known Activations