© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8880
    Prev
    Next
    INDEX
    Explanations

    explicit descriptions of sexual acts and bodily functions

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

    This neuron detects explicit sexual content and graphic descriptions of sexual acts.

    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
    zarchiwizowane
    -0.39
    chafter
    -0.37
     MutableLiveData
    -0.31
    奔
    -0.31
     virtu
    -0.30
     Rhein
    -0.29
    auff
    -0.29
    Xna
    -0.28
    出かけ
    -0.28
     visit
    -0.28
    POSITIVE LOGITS
     breathing
    0.80
     gasping
    0.79
     unconscious
    0.75
     fainted
    0.75
     consciousness
    0.75
     breaths
    0.73
    breathing
    0.73
     conscious
    0.73
     breathes
    0.73
     sobbing
    0.68
    Activations Density 0.321%

    No Known Activations