© 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. 25-GEMMASCOPE-RES-16K
    11. 2584
    Prev
    Next
    INDEX
    Explanations

    references to horror movie elements, particularly focusing on sound design and its impact on audience perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quiao
    -0.62
    UnsafeEnabled
    -0.60
     noqa
    -0.58
     Picchu
    -0.57
    
    -0.55
    weza
    -0.55
     BorderRadius
    -0.55
     Mayweather
    -0.55
    zeera
    -0.54
    AccessorTable
    -0.54
    POSITIVE LOGITS
     horror
    1.40
     Horror
    1.30
     spooky
    1.24
     haunted
    1.23
    Horror
    1.21
    horror
    1.18
     Halloween
    1.16
     creepy
    1.14
     Haunted
    1.10
     scary
    1.09
    Activations Density 0.562%

    No Known Activations