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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130002
    Prev
    Next
    INDEX
    Explanations

    references to licensing and ownership of software

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

    support received, mode explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.40
    XmlAttribute
    -0.38
    DeleteBehavior
    -0.37
    TypedValue
    -0.36
    createCell
    -0.35
     Baumann
    -0.35
     al
    -0.35
    balleur
    -0.34
    mergeFrom
    -0.34
     Paglinawan
    -0.34
    POSITIVE LOGITS
    ISupport
    1.08
    esModule
    0.59
    AutoresizingMask
    0.50
    supporting
    0.49
    Supporting
    0.49
    findpost
    0.49
    UnusedPrivate
    0.49
     Supporting
    0.48
    getSupport
    0.47
    stretchr
    0.47
    Activations Density 0.001%

    No Known Activations