© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10785
    Prev
    Next
    INDEX
    Explanations

    expressions and references that convey horror, shock, and outrage

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

    "horror" or "shock"

    np_acts-logits-general · gemini-2.0-flash

    horror and shock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    Tikang
    -0.54
    thâu
    -0.52
     dAtA
    -0.48
    +#+#
    -0.47
     Fighter
    -0.46
    onActivityResult
    -0.46
     spirited
    -0.45
    spirited
    -0.45
    Energ
    -0.44
     asser
    -0.43
    POSITIVE LOGITS
     horror
    1.31
    horror
    1.10
     horrors
    1.10
     horrifying
    1.09
     horrific
    1.05
     horrible
    1.05
     Horror
    1.04
     horrified
    1.02
    Horror
    1.02
     horri
    0.97
    Activations Density 0.322%

    No Known Activations