Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 277
    Prev
    Next
    INDEX
    Explanations

    elements of horror that evoke a sense of dread or psychological tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.65
     démission
    -0.51
    afel
    -0.48
    ীব
    -0.48
    ̀i
    -0.48
     słoń
    -0.48
    AnchorStyles
    -0.46
     <>",
    -0.46
    UnsafeEnabled
    -0.46
    sizeCache
    -0.46
    POSITIVE LOGITS
     horror
    1.43
     Halloween
    1.39
     spooky
    1.39
     Horror
    1.35
    Horror
    1.28
     scary
    1.25
     creepy
    1.25
    horror
    1.25
     halloween
    1.23
     haunted
    1.23
    Activations Density 0.332%

    No Known Activations