© 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. 2-GEMMASCOPE-RES-16K
    11. 13353
    Prev
    Next
    INDEX
    Explanations

    mentions of diversity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementGuid
    -0.57
     injustice
    -0.52
    difference
    -0.52
    reality
    -0.51
    fjspx
    -0.50
    variation
    -0.49
     ब्रेकडाउन
    -0.49
    differences
    -0.49
    variations
    -0.49
    RenderAtEndOf
    -0.48
    POSITIVE LOGITS
     diverse
    2.00
     varied
    1.89
    Diverse
    1.60
     Diverse
    1.56
    diverse
    1.51
     beragam
    1.13
     diversified
    1.10
     variadas
    1.10
     diversa
    1.09
     varying
    1.09
    Activations Density 0.210%

    No Known Activations