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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "percentage" and its variations

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

    percentage of

    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
    Draw
    -0.42
    Load
    -0.40
    In
    -0.38
     calda
    -0.36
     kanan
    -0.36
     secas
    -0.36
     grève
    -0.35
    <em>
    -0.35
     houten
    -0.35
    slee
    -0.35
    POSITIVE LOGITS
     percentage
    1.31
     Percentage
    1.23
    percentage
    1.18
     percentages
    1.13
    Percentage
    1.13
     percent
    1.05
    centages
    1.03
     pourcentage
    1.03
     porcentaje
    1.02
     (%)
    1.00
    Activations Density 0.019%

    No Known Activations