© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1309
    Prev
    Next
    INDEX
    Explanations

    references to gruesome or disturbing imagery related to death

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

    descriptions of dead bodies and corpses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.54
    protetor
    -0.49
     CURLOPT
    -0.45
    CURLOPT
    -0.44
    енча
    -0.44
     resourceCulture
    -0.42
     bicchiere
    -0.42
     négoci
    -0.42
    Chham
    -0.40
    abetes
    -0.40
    POSITIVE LOGITS
     corpse
    1.47
     corpses
    1.42
     cadáver
    1.20
    尸体
    1.12
     dead
    1.11
     carcasses
    1.05
    屍
    1.05
     cada
    1.05
     bodies
    1.02
     carcass
    1.00
    Activations Density 0.478%

    No Known Activations