© 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. 13679
    Prev
    Next
    INDEX
    Explanations

    technical notation and units related to measurements in scientific contexts

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

    Mathematical expressions or formulas

    np_acts-logits-general · gemini-2.0-flash

    scientific units and densities

    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
     كومونز
    -0.94
    copg
    -0.83
     snippetHide
    -0.81
    expandindo
    -0.75
    󠁮
    -0.74
    iſten
    -0.73
    dafx
    -0.71
    iſen
    -0.70
    Datuak
    -0.69
     незавершена
    -0.67
    POSITIVE LOGITS
    ๆ
    0.63
     illustrationer
    0.59
     Wikiseite
    0.57
     Gruber
    0.56
     ​​
    0.55
     enfans
    0.54
     Meksika
    0.52
     balení
    0.52
     věci
    0.52
     Bersama
    0.51
    Activations Density 3.171%

    No Known Activations