© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1590
    Prev
    Next
    INDEX
    Explanations

    references to horror themes and elements in literature or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.70
     campeones
    -0.55
    casecmp
    -0.50
    WithIOException
    -0.50
    bigoplus
    -0.49
    IsMutable
    -0.49
    ']")
    -0.48
     matahari
    -0.47
     fiecare
    -0.45
     StringTokenizer
    -0.45
    POSITIVE LOGITS
     horror
    1.05
     Horror
    1.05
    Horror
    1.04
    horror
    0.96
     haunted
    0.91
     creepy
    0.88
     Haunted
    0.86
     spooky
    0.85
     scary
    0.83
    Haunted
    0.82
    Activations Density 0.329%

    No Known Activations