© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102746
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and their variations

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

    had been previously

    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
     самой
    -0.28
    ArgsConstructor
    -0.27
    SC
    -0.25
    ヮ
    -0.25
     zippers
    -0.25
    witcher
    -0.25
    PS
    -0.25
    NameInMap
    -0.24
     самая
    -0.23
     самых
    -0.23
    POSITIVE LOGITS
     previously
    0.78
     wcześ
    0.77
     vorher
    0.73
     zuvor
    0.71
     sebelumnya
    0.70
     wcześniej
    0.69
     BoxDecoration
    0.68
     vroeger
    0.67
     earlier
    0.67
     préalable
    0.66
    Activations Density 0.038%

    No Known Activations