© 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. 10757
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate action or changes in state

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

    before mathematical or scientific symbols

    np_acts-logits-general · gemini-2.0-flash

    medical/scientific abbreviations and terms

    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
     législ
    -0.39
    pyl
    -0.37
    issime
    -0.35
    airs
    -0.35
    sunset
    -0.34
     gỗ
    -0.34
    MenuInflater
    -0.34
     nakalista
    -0.33
    scribe
    -0.33
     MediaQuery
    -0.33
    POSITIVE LOGITS
    principalColumn
    0.66
    LabelTagHelper
    0.60
    tagHelperRunner
    0.56
     therein
    0.52
    новниш
    0.50
    queryInterface
    0.50
    featureID
    0.49
    WebElementEntity
    0.49
    ⅘
    0.49
    vician
    0.48
    Activations Density 2.042%

    No Known Activations