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

    Neuronpedia

    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16148
    Prev
    Next
    INDEX
    Explanations

    elements related to character interactions and relationships in narratives

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

    references to named characters and lore within fantasy or sci‑fi plot summaries, especially proper nouns denoting people, places, and factions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    character names and descriptions in fictional narratives, particularly in fantasy or sci-fi contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    verifyException
    -0.70
     kaarangay
    -0.63
     resourceCulture
    -0.57
    [@BOS@]
    -0.57
    <unused28>
    -0.57
    <unused14>
    -0.57
    <unused42>
    -0.57
    ⤹
    -0.57
    <unused3>
    -0.57
    <unused8>
    -0.57
    POSITIVE LOGITS
     hero
    0.49
     protagonist
    0.43
    hero
    0.43
     héros
    0.40
     heroine
    0.36
     trainee
    0.36
     heroes
    0.35
     herói
    0.35
     journey
    0.34
     герой
    0.34
    Activations Density 0.328%

    No Known Activations