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. 5-GEMMASCOPE-RES-16K
    6. 1504
    Prev
    Next
    INDEX
    Explanations

    phrases related to contribution and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aud
    -0.51
    ICALS
    -0.49
    räck
    -0.49
    asă
    -0.47
     affid
    -0.47
    affaire
    -0.47
    ňov
    -0.47
     saída
    -0.46
     montagem
    -0.46
     viaj
    -0.46
    POSITIVE LOGITS
     contribution
    1.94
     contributions
    1.91
     contributing
    1.86
     contribute
    1.83
     Contribute
    1.81
     contributes
    1.78
     Contributions
    1.78
     contributed
    1.78
    Contribute
    1.76
     Contribution
    1.73
    Activations Density 0.144%

    No Known Activations