© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    terminologies related to chemical reactions and concentrations

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

    before bracketed abbreviations

    np_acts-logits-general · gemini-2.0-flash

    frugality, randomness, dart

    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
     Administrativna
    -0.55
    addGap
    -0.50
    ExtendWith
    -0.49
     المعيارى
    -0.49
    UrlEncoded
    -0.47
    SequentialGroup
    -0.46
    reportWebVitals
    -0.45
    NewUrlParser
    -0.44
     Witte
    -0.44
     khiển
    -0.43
    POSITIVE LOGITS
     CEST
    0.52
     Lighthouse
    0.52
     Paddington
    0.52
     Grange
    0.51
     vowels
    0.50
     Vaticano
    0.50
     Taro
    0.50
     gql
    0.49
     scones
    0.49
     Cæsar
    0.49
    Activations Density 1.374%

    No Known Activations