© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 51631
    Prev
    Next
    INDEX
    Explanations

    references to toxic substances and related terminology

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

    toxic elements

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SpringRunner
    -0.49
    Means
    -0.48
     Means
    -0.44
     Arrangement
    -0.44
     صفحۀ
    -0.44
     AppBar
    -0.44
     CPL
    -0.44
    rere
    -0.43
    Chú
    -0.43
    randa
    -0.43
    POSITIVE LOGITS
     toxic
    2.11
     Toxic
    2.11
    Toxic
    2.03
    toxic
    1.98
     TOXIC
    1.87
    TOXIC
    1.58
     toxicity
    1.51
     tóxic
    1.47
     poisonous
    1.34
     токси
    1.33
    Activations Density 0.011%

    No Known Activations