© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 100000
    Prev
    Next
    INDEX
    Explanations

    patterns or symbols in code related to formatting and output control

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

    programming and international words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ficha
    -0.40
     Krone
    -0.34
     situado
    -0.33
     meubles
    -0.33
     Asamblea
    -0.33
    期刊论文
    -0.33
     speaking
    -0.32
     République
    -0.32
     Erde
    -0.31
    有什么
    -0.31
    POSITIVE LOGITS
    tvguidetime
    0.85
     pinulongan
    0.79
     resourceCulture
    0.77
    expandindo
    0.72
     lenker
    0.69
     مشين
    0.68
    RegressionTest
    0.67
    قایناق‌لار
    0.64
    Geplaatst
    0.63
    OCCURRED
    0.63
    Activations Density 0.028%

    No Known Activations