© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications and their citations

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

    academic citation details and scientific publication references.

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

    bibliographic citations to physics journals, especially “Phys. Rev. Lett.”-style entries with volume/page numbers and formatting markers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    volume and issue numbers in academic journal citations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    ﷽
    -0.43
     Detal
    -0.43
     cristianismo
    -0.40
     dettaglio
    -0.40
     Zuge
    -0.39
    Gön
    -0.39
     kathol
    -0.38
    Skocz
    -0.37
    Véase
    -0.37
    Adj
    -0.37
    POSITIVE LOGITS
    PhysRevLett
    1.09
     Lett
    0.69
    Lett
    0.58
    ArrowToggle
    0.55
     letters
    0.53
    tagHelperRunner
    0.51
     letter
    0.50
     становника
    0.50
    letter
    0.48
    RegressionTest
    0.48
    Activations Density 0.128%

    No Known Activations