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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15322
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and discussions surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.79
     ſch
    -0.78
    ſelf
    -0.76
     iſt
    -0.74
    LLocation
    -0.71
     itſelf
    -0.69
     nakalista
    -0.69
    ￳
    -0.69
     Autorizaciones
    -0.68
    onViewCreated
    -0.67
    POSITIVE LOGITS
     earlier
    0.43
     previous
    0.39
     című
    0.39
     article
    0.37
     in
    0.35
     the
    0.34
     section
    0.33
     my
    0.33
     our
    0.32
     geladeira
    0.31
    Activations Density 0.901%

    No Known Activations