Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 122
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in code or markup syntax

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

    programming-related code syntax and technical/computational terminology.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     Chwiliwch
    -0.63
     kaarangay
    -0.50
     AssemblyTitle
    -0.48
    PMailer
    -0.48
    iſen
    -0.47
     muualla
    -0.45
     &___
    -0.44
    EditorBrowsable
    -0.43
     propOrder
    -0.42
     titolata
    -0.41
    POSITIVE LOGITS
    httphttps
    0.65
    addContainerGap
    0.54
     jScrollPane
    0.52
    ViewFeatures
    0.49
    enderror
    0.49
    endphp
    0.49
    WillAppear
    0.46
    UrlResolution
    0.43
    endgroup
    0.42
    )‏
    0.41
    Activations Density 0.767%

    No Known Activations