© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    references to levels of expression or contamination in biological samples

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

    Low levels, weak signals, or a slight amount of something

    np_acts-logits-general · gemini-2.0-flash

    low levels or weak intensity

    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
    dawnictwo
    -0.39
     carottes
    -0.35
     Vordergrund
    -0.34
    itamos
    -0.34
    YECTO
    -0.34
     maestra
    -0.34
    demás
    -0.34
     rodillas
    -0.33
     Diseño
    -0.33
     diseñada
    -0.33
    POSITIVE LOGITS
     briefly
    0.78
     slight
    0.73
    ьаж
    0.71
     occasional
    0.71
     Occasional
    0.67
    Slight
    0.67
     brief
    0.67
     weakly
    0.66
     occasionally
    0.66
    Occasionally
    0.65
    Activations Density 0.766%

    No Known Activations