© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13725
    Prev
    Next
    INDEX
    Explanations

    quantitative data and percentages

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

    Refers to percentages

    np_acts-logits-general · gemini-2.0-flash

    percentage values and context

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     диамет
    -0.38
     Nigel
    -0.38
     hornet
    -0.38
    Nigel
    -0.37
    Pico
    -0.35
     bij
    -0.35
     diameter
    -0.34
    stuk
    -0.34
    diameter
    -0.33
     pits
    -0.33
    POSITIVE LOGITS
     percentage
    1.07
    percentage
    1.02
     porcentaje
    1.00
     Percentage
    0.99
     percent
    0.96
     (%)
    0.94
    Percentage
    0.94
    percent
    0.93
     percentages
    0.92
     PERCENT
    0.90
    Activations Density 1.749%

    No Known Activations