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. 23902
    Prev
    Next
    INDEX
    Explanations

    attributes related to aesthetics and functionality in design

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

    descriptive characteristics

    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
    UnitTesting
    -0.76
    OGND
    -0.73
     utafitiHapana
    -0.68
    DockStyle
    -0.66
    ValueStyle
    -0.66
    ScopeManager
    -0.65
     InputDecoration
    -0.65
    migrationBuilder
    -0.64
     disambiguazione
    -0.63
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
     philanthropic
    0.37
     particular
    0.32
     novel
    0.31
     contemplative
    0.31
     hyper
    0.31
     focus
    0.31
     pandemic
    0.31
     esoteric
    0.30
     thing
    0.29
     minimalist
    0.29
    Activations Density 0.088%

    No Known Activations