Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 121861
    Prev
    Next
    INDEX
    Explanations

    terms associated with abuse and derogatory behavior

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

    abusive, oppressive, toxic

    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
    viewDidLoad
    -0.54
     ujednoznacz
    -0.54
     recreation
    -0.49
    hasMoreElements
    -0.49
     regola
    -0.46
    Recommendation
    -0.46
    rscheinlichkeit
    -0.46
    MeasureSpec
    -0.46
    SerializeField
    -0.46
    Recreation
    -0.46
    POSITIVE LOGITS
     abusive
    1.66
     abusi
    0.98
     oppressive
    0.84
     toxic
    0.70
     abuser
    0.66
     Toxic
    0.65
     Aggressive
    0.65
    abu
    0.65
     predatory
    0.65
    Aggressive
    0.62
    Activations Density 0.014%

    No Known Activations