© 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. 20-GEMMASCOPE-RES-131K
    11. 20056
    Prev
    Next
    INDEX
    Explanations

    features related to comparison and contrast, particularly in contexts involving options, examples, and classifications

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

    numbers and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    contentLoaded
    -0.63
    脚注の使い方
    -0.57
    تقاوى
    -0.49
    mybatisplus
    -0.46
     Roskov
    -0.46
    Viitteet
    -0.44
    addCriterion
    -0.43
     giù
    -0.43
    Enllaces
    -0.42
    Panamoan
    -0.42
    POSITIVE LOGITS
    Бахар
    0.46
    GraphicsUnit
    0.43
    sinki
    0.40
    formKey
    0.40
    celes
    0.38
    kheim
    0.37
    klen
    0.37
    DIPSETTING
    0.35
     foret
    0.35
     GenerationType
    0.35
    Activations Density 0.263%

    No Known Activations