© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6697
    Prev
    Next
    INDEX
    Explanations

    inquiries or questions posed in the text

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

    Questions or question-related words

    np_acts-logits-general · gemini-2.0-flash

    asking questions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tonode
    -0.62
    хьтан
    -0.60
    MemoryWarning
    -0.56
     ब्रेकडाउन
    -0.56
    GOTREF
    -0.55
     autorytatywna
    -0.52
     vectorielles
    -0.52
     للاسماء
    -0.52
     snippetHide
    -0.50
     numériques
    -0.49
    POSITIVE LOGITS
     question
    0.98
     questions
    0.87
     pregunta
    0.76
    question
    0.75
    Questions
    0.75
     Question
    0.75
     Questions
    0.74
     QUESTIONS
    0.73
    questions
    0.71
     questioned
    0.71
    Activations Density 0.417%

    No Known Activations