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. 21-GEMMASCOPE-RES-16K
    6. 6937
    Prev
    Next
    INDEX
    Explanations

    elements related to geometric operations and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    ReusableCell
    -0.66
    fread
    -0.53
     Consolidated
    -0.50
     propOrder
    -0.48
     Mounts
    -0.47
     jScrollPane
    -0.47
    ibos
    -0.46
     carousel
    -0.46
    psia
    -0.46
    IsContent
    -0.45
    POSITIVE LOGITS
     points
    1.08
     point
    0.98
    points
    0.91
     line
    0.89
     intersection
    0.87
    point
    0.84
     Points
    0.84
     Point
    0.82
    Points
    0.80
     puntos
    0.80
    Activations Density 0.809%

    No Known Activations