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. 12880
    Prev
    Next
    INDEX
    Explanations

    key concepts and structures related to formal arguments and claims in legal or analytical contexts

    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
     Houſe
    -1.01
     Efq
    -0.98
     Monfieur
    -0.94
     Jefus
    -0.93
     houſe
    -0.93
     faſt
    -0.92
     ſmall
    -0.90
     Theſe
    -0.89
     iſt
    -0.88
     ſy
    -0.86
    POSITIVE LOGITS
    <eos>
    0.60
     and
    0.56
     too
    0.52
    textbf
    0.51
    尤其
    0.47
     particuli
    0.47
     particularly
    0.47
    ,
    0.46
     mentioned
    0.45
     [
    0.45
    Activations Density 0.658%

    No Known Activations