© 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. 23-GEMMASCOPE-RES-16K
    11. 9640
    Prev
    Next
    INDEX
    Explanations

    references to ethnicities or classifications of groups, particularly in historical or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -1.06
    expandindo
    -0.96
     <>",
    -0.93
    EDEFAULT
    -0.93
     ujednoznacz
    -0.88
     surla
    -0.87
     propOrder
    -0.84
    AndEndTag
    -0.83
    évaluateur
    -0.79
    Parcelize
    -0.77
    POSITIVE LOGITS
     each
    0.66
     respective
    0.56
     jeweiligen
    0.54
     jeweils
    0.52
    Each
    0.52
    each
    0.51
     masing
    0.51
    各
    0.50
     Each
    0.49
     separate
    0.46
    Activations Density 1.025%

    No Known Activations