© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7916
    Prev
    Next
    INDEX
    Explanations

    algorithmic and programming-related structures or elements

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

    Code delimiters or punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.75
     linkovi
    -0.73
     propOrder
    -0.68
    ftagPool
    -0.67
    SourceChecksum
    -0.62
    Jereo
    -0.61
    webElementXpaths
    -0.60
    UnusedPrivate
    -0.60
    出版年
    -0.60
    postsleuth
    -0.59
    POSITIVE LOGITS
    <eos>
    0.40
     prim
    0.38
     
    0.36
    fastjson
    0.35
    ratt
    0.34
    ↵↵↵↵↵↵↵↵
    0.34
    ___
    0.33
    scope
    0.33
    ──
    0.33
    ↵↵↵↵↵
    0.32
    Activations Density 4.617%

    No Known Activations