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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103598
    Prev
    Next
    INDEX
    Explanations

    structural elements of a story or narrative, such as chapters and character introductions

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

    The beginning of story chapters, narratives, or quoted text that follows chapter headings, date markers, or section breaks (often indicated by asterisks or formatting).

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Numerade
    -0.85
     ब्रेकडाउन
    -0.81
     صوتيه
    -0.80
     Infórmanos
    -0.75
     للمعارف
    -0.75
    MessageOf
    -0.73
    majánló
    -0.70
     Exacts
    -0.68
     незавершена
    -0.67
    ➯
    -0.66
    POSITIVE LOGITS
    ing
    0.40
     day
    0.40
     Mis
    0.36
     Ord
    0.35
     was
    0.35
     black
    0.35
    black
    0.35
     pan
    0.33
     date
    0.33
     lines
    0.32
    Activations Density 0.010%

    No Known Activations