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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13501
    Prev
    Next
    INDEX
    Explanations

    references to gender and race-related discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chỉnh
    -0.49
    tralight
    -0.46
     sánh
    -0.45
    IUrlHelper
    -0.45
    kary
    -0.43
    Sizes
    -0.43
    σμο
    -0.42
     arvio
    -0.41
    etap
    -0.41
    aj
    -0.41
    POSITIVE LOGITS
     незавершена
    0.83
     hObject
    0.83
    ništ
    0.76
    RetentionPolicy
    0.73
     utafitiHapana
    0.73
     CreateTagHelper
    0.73
    extAlignment
    0.73
    بوابة
    0.70
    IBOutlet
    0.70
     being
    0.69
    Activations Density 0.657%

    No Known Activations