Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 103138
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and related forms

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

    The token "is" (or similar linking verbs) functioning as the main predicate connecting a subject that identifies a key concept/problem with an explanation or elaboration that follows, typically in academic or formal text.

    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
    tagez
    -0.45
     GlobalKey
    -0.45
    ElementException
    -0.39
    bus
    -0.38
     свое
    -0.38
     tagName
    -0.38
    LayoutPanel
    -0.37
     fVar
    -0.37
    enaam
    -0.37
    abetta
    -0.36
    POSITIVE LOGITS
     surla
    0.70
    parsedMessage
    0.56
     tartalomajánló
    0.54
    adaptiveStyles
    0.52
    tagHelperRunner
    0.52
    ValueStyle
    0.51
    Jîn
    0.46
    rungsseite
    0.44
     Preferencias
    0.44
    Jeografia
    0.43
    Activations Density 0.087%

    No Known Activations