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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 8667
    Prev
    Next
    INDEX
    Explanations

    actions related to completing tasks or carrying out responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dumont
    -0.87
     Mathis
    -0.71
     theta
    -0.71
     Dud
    -0.70
    tamen
    -0.70
    Dud
    -0.68
     smtplib
    -0.68
     ambientales
    -0.68
     Bennett
    -0.68
     Neust
    -0.68
    POSITIVE LOGITS
     carried
    1.78
     carry
    1.77
     carries
    1.75
     Carry
    1.72
    carry
    1.69
     CARRY
    1.65
     Carried
    1.62
    Carry
    1.57
    carried
    1.54
     carrying
    1.48
    Activations Density 0.073%

    No Known Activations