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. 20-GEMMASCOPE-RES-16K
    6. 581
    Prev
    Next
    INDEX
    Explanations

    instances of hashtags in programming or markup contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inheit
    -0.63
    ={({
    -0.61
     Ove
    -0.57
    %{
    -0.56
    "));
    
    -0.56
    fürst
    -0.56
    Saluti
    -0.56
    Compiled
    -0.55
    afy
    -0.54
    Osob
    -0.54
    POSITIVE LOGITS
    .#
    1.22
     #
    1.10
     noqa
    1.04
    \#
    1.04
    -#
    1.00
     (#
    0.96
    \#\#
    0.96
     \#
    0.95
     $\#
    0.93
    /#
    0.93
    Activations Density 0.232%

    No Known Activations