© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15892
    Prev
    Next
    INDEX
    Explanations

    references to professional certifications and qualifications in various fields

    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
     ExecuteAsync
    -0.79
    CodedInputStream
    -0.77
    unknownFields
    -0.74
    parsedMessage
    -0.63
    AndEndTag
    -0.59
    BarStyle
    -0.59
    awtextra
    -0.58
     rake
    -0.57
    djangoproject
    -0.56
    étaient
    -0.56
    POSITIVE LOGITS
     certification
    0.97
     certified
    0.93
     Certified
    0.82
    certified
    0.79
    Certified
    0.77
     certific
    0.77
     certifications
    0.74
     Certification
    0.73
     certify
    0.68
     qualification
    0.65
    Activations Density 0.093%

    No Known Activations