© 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. 40576
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts, particularly those involving units and geometric structures

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

    complex shape cd filter

    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
    XmlAccessType
    -0.43
     traditionnels
    -0.42
     initComponents
    -0.42
    égard
    -0.40
     umana
    -0.38
     visitare
    -0.37
     tilf
    -0.37
    licó
    -0.37
    explique
    -0.37
     ніж
    -0.36
    POSITIVE LOGITS
    fromnode
    0.70
    
    0.60
    vician
    0.55
    Архівовано
    0.51
    expandindo
    0.51
    󠁿
    0.47
     ویکی‌پدی
    0.47
    motive
    0.45
     يتيمه
    0.45
    bosky
    0.45
    Activations Density 0.122%

    No Known Activations