© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13228
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to code, specifically function definitions and control statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ब्रेकडाउन
    -1.04
     kaarangay
    -0.88
    OGND
    -0.84
     мәкал
    -0.82
    出版年
    -0.80
    WriteTagHelper
    -0.80
     lenker
    -0.78
    featureID
    -0.77
    ChildScrollView
    -0.77
    تقاوى
    -0.75
    POSITIVE LOGITS
    <b>
    0.53
    0
    0.48
    //
    0.48
    [toxicity=0]
    0.47
     other
    0.47
    <strong>
    0.46
    .
    0.44
     and
    0.44
    1
    0.43
    {
    0.43
    Activations Density 0.183%

    No Known Activations