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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106734
    Prev
    Next
    INDEX
    Explanations

    components and systems related to energy distribution and optimization

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

    exothermic body, friction condition, frequency signal, driving integrated

    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
     îna
    -0.39
    aurait
    -0.38
     Inscrivez
    -0.38
    PushMatrix
    -0.38
    ędziesz
    -0.35
     largura
    -0.35
    ereum
    -0.34
     bump
    -0.34
     whatever
    -0.34
     maternidade
    -0.33
    POSITIVE LOGITS
     Normdatei
    0.75
     otomatig
    0.64
    parsedMessage
    0.58
     Roskov
    0.56
    ChildScrollView
    0.55
    GEBURTSDATUM
    0.54
    الحياه
    0.53
     TextInputType
    0.53
     LoggerFactory
    0.52
    hereinafter
    0.51
    Activations Density 0.072%

    No Known Activations