© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5473
    Prev
    Next
    INDEX
    Explanations

    specific programming and coding elements

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

    programming or technical syntax elements, like variable names, function parameters, and code structure tokens.

    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
    ↵↵
    -0.32
    <eos>
    -0.32
    <em>
    -0.30
     придется
    -0.29
    <strong>
    -0.29
    <h1>
    -0.28
     It
    -0.28
    ../
    -0.28
    It
    -0.27
     (
    -0.27
    POSITIVE LOGITS
    LookAnd
    1.05
    uxxxx
    0.98
    Personensuche
    0.91
    MLLoader
    0.90
    ViewFeatures
    0.89
    AddTagHelper
    0.88
    Diweddarwch
    0.85
     
    0.83
     resourceCulture
    0.82
    exitRule
    0.82
    Activations Density 0.545%

    No Known Activations