© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 973
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical concepts and troubleshooting

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

    French text or non-English characters, particularly accented characters like é, ê, and à.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    non-English language text, particularly words with accent marks or special characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Arzt
    -0.43
     you
    -0.42
     Erde
    -0.42
    you
    -0.42
    if
    -0.42
    I
    -0.42
     Geduld
    -0.42
     Bạn
    -0.40
    You
    -0.40
     Wege
    -0.39
    POSITIVE LOGITS
    iſen
    1.03
    iſten
    0.95
     ſind
    0.90
     ivelany
    0.88
     المعيارى
    0.88
    niſſe
    0.88
    arangay
    0.87
     мәкал
    0.87
    تقاوى
    0.86
    ésultats
    0.84
    Activations Density 0.085%

    No Known Activations