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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 10776
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations in the context of invitations or requests for participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chera
    -0.75
     Rauch
    -0.63
    rxjs
    -0.61
     Allentown
    -0.60
     Ehrlich
    -0.57
     ehr
    -0.57
     استنادى
    -0.56
    람
    -0.56
    רה
    -0.56
    testnet
    -0.56
    POSITIVE LOGITS
     join
    2.71
     joining
    2.60
     joins
    2.59
     Joining
    2.51
     JOIN
    2.49
     joined
    2.41
    Joining
    2.36
     Join
    2.33
     Joins
    2.33
    join
    2.33
    Activations Density 0.045%

    No Known Activations