© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    technical notations and symbols used in scientific contexts

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

    numerical and alphabetical elements in technical or mathematical notation, particularly subscripts, indices, and reference identifiers.

    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
     мәкал
    -0.62
    SourceChecksum
    -0.49
    sizeCache
    -0.48
    hoeddwyd
    -0.48
    Autoritní
    -0.48
     ErrIntOverflow
    -0.45
    oa̍t
    -0.44
     Turquie
    -0.44
    tagHelperRunner
    -0.42
     Chwiliwch
    -0.42
    POSITIVE LOGITS
     main
    0.53
     Main
    0.52
    Main
    0.52
     AOS
    0.49
     Royal
    0.47
    NOPQRST
    0.47
    🟤
    0.47
     royal
    0.47
     mood
    0.47
     DFS
    0.47
    Activations Density 0.865%

    No Known Activations