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. 10-GEMMASCOPE-RES-16K
    6. 13150
    Prev
    Next
    INDEX
    Explanations

    information related to workplace roles and responsibilities, particularly about gender-related employment issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.89
    Portale
    -0.85
     houſe
    -0.79
     purpoſe
    -0.79
     ſmall
    -0.75
     chi̍t
    -0.75
     preſent
    -0.74
     laſt
    -0.74
     greateſt
    -0.73
    hematical
    -0.72
    POSITIVE LOGITS
     that
    1.04
     where
    0.89
     whose
    0.82
     which
    0.71
     of
    0.67
     who
    0.63
     thats
    0.60
    ที่
    0.59
    that
    0.59
     with
    0.56
    Activations Density 1.022%

    No Known Activations