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. 20-GEMMASCOPE-RES-131K
    6. 122697
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and symbols

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

    Empty delimiter marks transitions between sections, formula components, or document segments in technical and legal texts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     AssemblyCulture
    -0.66
    ########.
    -0.59
    期刊论文
    -0.59
    MigrationBuilder
    -0.56
     المعيارى
    -0.54
    IUrlHelper
    -0.53
    ValueStyle
    -0.52
     AssemblyVersion
    -0.52
     defaultstate
    -0.52
     الحره
    -0.51
    POSITIVE LOGITS
     fos
    0.36
     ſte
    0.36
    parsedMessage
    0.32
     дописавши
    0.31
     Jail
    0.31
     kaarangay
    0.31
    Geografie
    0.31
     Fos
    0.30
    *)((
    0.30
    TypedDataSet
    0.29
    Activations Density 0.091%

    No Known Activations