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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 34096
    Prev
    Next
    INDEX
    Explanations

    terms related to white supremacy and associated concepts

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

    fascist racist extremist ideologies

    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
     Pert
    -0.43
    adaptiveStyles
    -0.40
    兜
    -0.39
     ujednoznacz
    -0.38
    俏
    -0.38
     당
    -0.37
     pere
    -0.37
    rénées
    -0.36
    iestety
    -0.36
    egl
    -0.36
    POSITIVE LOGITS
    cist
    1.61
    cists
    1.24
     suprema
    1.01
    remacy
    0.96
     supremacy
    0.93
    cism
    0.84
    cista
    0.81
     racist
    0.78
     dominance
    0.73
     Suprema
    0.68
    Activations Density 0.008%

    No Known Activations