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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57063
    Prev
    Next
    INDEX
    Explanations

    bracelet-like structures or patterns within mathematical expressions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AsUp
    -1.07
    +#+#
    -1.05
    createCanvas
    -1.01
    DockStyle
    -0.98
     Jefus
    -0.96
    UnitTesting
    -0.96
     TextInputType
    -0.96
    picasso
    -0.95
     ddelweddau
    -0.95
    contentLoaded
    -0.94
    POSITIVE LOGITS
    {
    0.68
    {"
    0.63
     “
    0.59
    jad
    0.57
     pes
    0.56
    віч
    0.56
    <sup>
    0.55
    混
    0.54
     {
    0.54
     ec
    0.53
    Activations Density 0.019%

    No Known Activations