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. 65091
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to rounding numbers to the nearest whole number or decimal place

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

    rounding to the nearest

    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
     كومونز
    -0.59
    VersionUID
    -0.52
     uVar
    -0.50
    Geplaatst
    -0.49
    tangentMode
    -0.48
    featureID
    -0.47
    providedIn
    -0.47
    Pek
    -0.46
    ubus
    -0.46
     հղումներ
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.46
     jaula
    0.44
     terpisah
    0.44
     craindre
    0.43
     Италијани
    0.42
     aveug
    0.42
     Constitucional
    0.41
     Begründung
    0.41
     autorytatywna
    0.40
     sekal
    0.40
    Activations Density 0.066%

    No Known Activations