© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58867
    Prev
    Next
    INDEX
    Explanations

    terms related to items that are used or have been in service long enough to show signs of wear

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

    state of being worn

    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
    脚注の使い方
    -0.68
    jspb
    -0.53
    IntoConstraints
    -0.52
    mybatisplus
    -0.49
    nextInt
    -0.48
     consig
    -0.48
    thansa
    -0.48
     getResult
    -0.48
     loto
    -0.48
     dehydration
    -0.47
    POSITIVE LOGITS
     worn
    1.78
    worn
    1.59
     Worn
    1.49
     wore
    1.07
    wear
    0.76
     wears
    0.75
     wear
    0.73
    Wear
    0.71
     Wear
    0.71
     indoss
    0.65
    Activations Density 0.004%

    No Known Activations