© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12992
    Prev
    Next
    INDEX
    Explanations

    mentions of experts and expertise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.75
    parsedMessage
    -0.74
    alamus
    -0.71
    nestjs
    -0.70
    cauc
    -0.69
     albicans
    -0.68
    łasz
    -0.66
    PreferredItem
    -0.65
     Searle
    -0.65
    charest
    -0.64
    POSITIVE LOGITS
     experts
    1.12
     Expert
    1.03
     expert
    1.00
     expertise
    1.00
    Expert
    0.99
    pertise
    0.99
     Experts
    0.98
     EXPERT
    0.96
    Expertise
    0.96
     expertos
    0.91
    Activations Density 0.037%

    No Known Activations