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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6403
    Prev
    Next
    INDEX
    Explanations

    specific computer vision related data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.78
    ReusableCell
    -0.70
     IndexPath
    -0.59
    useState
    -0.57
     evolucion
    -0.54
     &[
    -0.53
     آور
    -0.53
    !("{
    -0.53
    LLocation
    -0.53
    opla
    -0.53
    POSITIVE LOGITS
     cv
    1.03
    cv
    0.96
     مشين
    0.80
     Monfieur
    0.80
    Viki
    0.69
     Cv
    0.69
    الدراسه
    0.68
     mirror
    0.67
    Cv
    0.66
     Miro
    0.65
    Activations Density 0.038%

    No Known Activations