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. 13-GEMMASCOPE-RES-16K
    6. 11791
    Prev
    Next
    INDEX
    Explanations

    terms related to expertise and specialists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cauc
    -0.71
     Naidu
    -0.71
    parsedMessage
    -0.69
    writerow
    -0.69
     albicans
    -0.68
     Hogarth
    -0.68
    alamus
    -0.67
    שמי
    -0.67
    {§
    -0.67
    TypedDataSet
    -0.66
    POSITIVE LOGITS
     experts
    1.24
     expert
    1.21
     Expert
    1.17
     expertise
    1.16
    Expert
    1.10
     EXPERT
    1.08
     Experts
    1.02
    Expertise
    1.01
    expert
    0.99
     Expertise
    0.99
    Activations Density 0.058%

    No Known Activations