© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12191
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear physics and reactions

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

    terms related to nuclear physics, particularly atomic particles, energy levels, and interactions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delegate
    -0.38
     Roskov
    -0.38
    bruch
    -0.37
    NP
    -0.37
    ppen
    -0.37
    SPJ
    -0.36
     Gep
    -0.36
    synthesize
    -0.35
     Breaking
    -0.35
     Hume
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.50
     compacto
    0.49
    новништво
    0.47
     vegetación
    0.45
     الرياضيه
    0.45
    EDEFAULT
    0.45
    ыгана
    0.43
    Jîn
    0.43
     Schließlich
    0.43
    Panamoan
    0.43
    Activations Density 0.338%

    No Known Activations