© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    mathematically expressed relationships involving ratios and comparisons

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

    Mathematical or biological ratios

    np_acts-logits-general · gemini-2.0-flash

    ratio, proportion, variation

    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
    Sleep
    -0.34
     sleepers
    -0.32
    sleep
    -0.32
    SequentialGroup
    -0.30
     tả
    -0.30
     visiteurs
    -0.30
    som
    -0.30
     sleeping
    -0.29
     sitios
    -0.29
    ftant
    -0.29
    POSITIVE LOGITS
     ratio
    0.83
     CreateTagHelper
    0.79
     ratios
    0.77
     Ratio
    0.77
    IntoConstraints
    0.76
    Ratio
    0.68
     Ratios
    0.67
    ratio
    0.67
     RATIO
    0.66
    xrTableCell
    0.64
    Activations Density 1.238%

    No Known Activations