© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105782
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Personensuche
    -0.38
    Архівовано
    -0.38
     ब्रेकडाउन
    -0.38
     referrerpolicy
    -0.37
    Zeneca
    -0.37
    styleType
    -0.36
    XmlAccessorType
    -0.35
    msgstr
    -0.34
    хьтан
    -0.34
     uVar
    -0.34
    POSITIVE LOGITS
     question
    0.71
     questions
    0.66
    question
    0.61
     problem
    0.59
    problem
    0.54
     Question
    0.54
     Problem
    0.51
     problems
    0.51
    PreferredItem
    0.50
     प्रश्न
    0.50
    Activations Density 0.084%

    No Known Activations