© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2652
    Prev
    Next
    INDEX
    Explanations

    references to data presentation and formats in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedals
    -0.58
    deva
    -0.57
     oes
    -0.57
     gos
    -0.54
    NSNotification
    -0.54
     Hess
    -0.53
     szcze
    -0.53
     truth
    -0.53
    onova
    -0.52
     Donald
    -0.51
    POSITIVE LOGITS
    ("[
    1.16
     '[
    1.12
    $[
    1.12
     $[
    1.11
     $[\
    1.09
    ('[
    1.07
    $[\
    1.06
    .[
    1.05
    {[
    1.05
    >[
    1.04
    Activations Density 1.201%

    No Known Activations