© 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. 80851
    Prev
    Next
    INDEX
    Explanations

    references to vampires and their characteristics in literature

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

    vampire literature and young adult

    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
     mortar
    -0.49
    wegg
    -0.48
    ureux
    -0.47
    StructEnd
    -0.46
    Jerry
    -0.46
    breadcrumbs
    -0.43
    grie
    -0.43
    난
    -0.43
    Coarse
    -0.43
     coarse
    -0.43
    POSITIVE LOGITS
     vampire
    1.17
     Vampire
    1.08
     vampires
    1.04
    vampire
    1.00
    Vampire
    0.98
     Vamp
    0.93
     vamp
    0.82
    Vamp
    0.80
     Dracula
    0.80
    Dracula
    0.73
    Activations Density 0.012%

    No Known Activations