© 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. 14064
    Prev
    Next
    INDEX
    Explanations

    references to programming, coding, or database-related concepts

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

    following specific nouns

    np_acts-logits-general · gemini-2.0-flash

    genome assembly, phylogenetic trees, contract negotiations

    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
    #
    -0.56
    XDECREF
    -0.46
    contentLoaded
    -0.44
    ?}",
    -0.42
     /*#__
    -0.42
    SharedDtor
    -0.41
    __.__
    -0.41
    __))
    -0.41
     ویکی‌پدی
    -0.40
    pean
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.66
     surla
    0.52
    évaluateur
    0.49
     betweenstory
    0.48
    transQ
    0.48
     productivo
    0.48
     lèvres
    0.45
     disponibilités
    0.45
    FormTagHelper
    0.44
    AndEndTag
    0.44
    Activations Density 2.026%

    No Known Activations