© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14754
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or lists with elements related to games and media

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

    Numbers and arithmetic expressions

    np_acts-logits-general · gemini-2.0-flash

    sequences of numbers and mathematical expressions

    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
    -0.60
     jsPsych
    -0.56
    ⪜
    -0.56
     tartalo
    -0.51
     فريبيس
    -0.51
    Rhestr
    -0.50
    exitRule
    -0.48
    kadot
    -0.48
     ſind
    -0.47
     beſti
    -0.47
    POSITIVE LOGITS
    writerow
    0.40
     PeEnEo
    0.35
    EndContext
    0.35
     menik
    0.35
     correctes
    0.32
     हों
    0.31
     mł
    0.30
    igshid
    0.30
     aika
    0.30
     mengal
    0.30
    Activations Density 0.933%

    No Known Activations