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. 29632
    Prev
    Next
    INDEX
    Explanations

    references to educational courses and teaching activities

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

    academic courses and teaching

    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
    MessageOf
    -0.39
    endosi
    -0.37
    amb
    -0.35
     bulunur
    -0.35
    urlpatterns
    -0.34
    oman
    -0.33
    خدام
    -0.32
    quiel
    -0.32
     Grimal
    -0.31
     habido
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.66
    HandlerContext
    0.59
     semester
    0.49
    taught
    0.49
     autorytatywna
    0.48
    RenderAtEndOf
    0.48
     Semester
    0.47
    tagext
    0.47
    Instructor
    0.47
     houſe
    0.46
    Activations Density 0.022%

    No Known Activations