© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs related to types and functions

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    initial value

    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
    transQ
    -0.68
     AttributeSet
    -0.60
    tagHelperRunner
    -0.60
    ="@+
    -0.60
     مرئيه
    -0.56
    RegressionTest
    -0.56
    Билгалдахарш
    -0.54
    webElementXpaths
    -0.52
    styleable
    -0.52
    تقاوى
    -0.52
    POSITIVE LOGITS
     AssemblyTitle
    0.38
    Источники
    0.33
     tré
    0.32
     raya
    0.32
    setFirstName
    0.32
     somebody
    0.31
     skole
    0.31
     IOError
    0.30
     åp
    0.30
    Whatever
    0.30
    Activations Density 0.553%

    No Known Activations