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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30358
    Prev
    Next
    INDEX
    Explanations

    references to horror and related themes

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

    horror stories, films, or tales

    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
    iqué
    -0.59
     pse
    -0.57
    swick
    -0.53
    ⟬
    -0.53
     PSE
    -0.52
     tickle
    -0.52
     Sext
    -0.52
     tse
    -0.52
    己
    -0.52
     Twee
    -0.51
    POSITIVE LOGITS
     Horror
    1.05
    horror
    1.00
     horror
    0.99
    Horror
    0.99
     horrors
    0.74
     Horowitz
    0.71
     Hor
    0.69
     horrified
    0.65
     corrupción
    0.64
     HOR
    0.63
    Activations Density 0.005%

    No Known Activations