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. 65179
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to music adaptations and performances

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

    worldwide distribution and editions

    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
    Personendaten
    -0.84
    setVerticalGroup
    -0.84
    новништво
    -0.83
     ब्रेकडाउन
    -0.83
     незавершена
    -0.79
     propOrder
    -0.77
    enterOuterAlt
    -0.75
     betweenstory
    -0.75
     jspb
    -0.73
    MigrationBuilder
    -0.71
    POSITIVE LOGITS
    undred
    0.31
     worldwide
    0.29
     many
    0.29
     widely
    0.29
     copies
    0.27
    bagai
    0.27
     franchises
    0.27
     copy
    0.27
     across
    0.27
     clubs
    0.27
    Activations Density 0.042%

    No Known Activations