© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95877
    Prev
    Next
    INDEX
    Explanations

    taxonomy-related terms, specifically focusing on moth and beetle families

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

    taxonomic family names

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     $_-
    -0.88
     disambiguazione
    -0.88
     pinulongan
    -0.85
    <unused73>
    -0.85
    <unused17>
    -0.85
    <unused7>
    -0.85
    <unused42>
    -0.84
    <unused58>
    -0.84
    <unused28>
    -0.84
    <unused15>
    -0.84
    POSITIVE LOGITS
    idae
    0.73
    laceae
    0.68
    ceae
    0.64
    cidae
    0.63
    aceae
    0.63
    iaceae
    0.47
    ridae
    0.44
    IDAE
    0.43
    paravant
    0.39
    lidae
    0.39
    Activations Density 0.017%

    No Known Activations