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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6293
    Prev
    Next
    INDEX
    Explanations

    references to lead, particularly in the context of health effects and environmental exposure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.75
     CreateTagHelper
    -0.63
    onedDateTime
    -0.56
    anInt
    -0.54
    ylde
    -0.54
    hlungen
    -0.53
     oscillation
    -0.52
    ideen
    -0.52
    AddHtmlAttribute
    -0.52
    SizeF
    -0.52
    POSITIVE LOGITS
     lead
    3.24
    lead
    2.76
     Lead
    2.70
    Lead
    2.68
     leads
    2.66
     Leads
    2.30
    leads
    2.30
     LEAD
    2.25
    Leads
    2.18
    LEAD
    2.01
    Activations Density 0.122%

    No Known Activations