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. 8753
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations, indicating an emphasis on participation and collaboration

    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
     lượng
    -0.60
     Allentown
    -0.58
    chera
    -0.58
    Ulrich
    -0.57
    רה
    -0.57
    awang
    -0.55
     Voltaire
    -0.55
     Rauch
    -0.54
     Lehigh
    -0.53
    crm
    -0.53
    POSITIVE LOGITS
     JOIN
    1.68
     joins
    1.67
     join
    1.67
     joining
    1.64
     Joining
    1.61
     Joins
    1.59
    join
    1.56
    JOIN
    1.55
     Join
    1.47
    Joining
    1.45
    Activations Density 0.051%

    No Known Activations