© 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. 12375
    Prev
    Next
    INDEX
    Explanations

    instances of synchronized code blocks or statements in programming

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

    Code or text referencing locks

    np_acts-logits-general · gemini-2.0-flash

    programming locks and mutexes

    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
    ⓧ
    -0.53
    脚注の使い方
    -0.50
     Jurí
    -0.48
    ########.
    -0.47
    DoubleQuotes
    -0.47
    ForResult
    -0.47
     venuto
    -0.47
     Escolar
    -0.46
    ppuden
    -0.45
    étoit
    -0.44
    POSITIVE LOGITS
    mutex
    0.54
    semaphore
    0.47
     lock
    0.45
     guard
    0.45
    Lock
    0.44
     mutex
    0.44
    Mutex
    0.43
     Lock
    0.42
    lock
    0.42
    maphore
    0.41
    Activations Density 0.165%

    No Known Activations