© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4249
    Prev
    Next
    INDEX
    Explanations

    elements related to horror themes and their structural components in storytelling

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

    "Horror" or related terms

    np_acts-logits-general · gemini-2.0-flash

    horror movie descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.55
    opress
    -0.55
    NameInMap
    -0.51
    TagMode
    -0.51
     administrativos
    -0.50
     برانيه
    -0.49
    ']")
    -0.49
     lute
    -0.49
     apaixon
    -0.48
     démission
    -0.48
    POSITIVE LOGITS
     horror
    1.27
     Horror
    1.17
    Horror
    1.14
    horror
    1.10
     scary
    0.87
     gore
    0.86
     creepy
    0.82
     terror
    0.81
     spooky
    0.79
     scaring
    0.78
    Activations Density 0.262%

    No Known Activations