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. 2359
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets related to creating styles and handling JSON data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or JSON-like structures

    np_acts-logits-general · gemini-2.0-flash

    start of object literal

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     يتيمه
    -0.41
     quý
    -0.36
     [];
    
    -0.36
     negativ
    -0.34
     atas
    -0.34
     courant
    -0.33
     rem
    -0.33
    セス
    -0.33
    ilov
    -0.33
     cannes
    -0.32
    POSITIVE LOGITS
    ({
    1.21
     {'
    1.16
    ({
    
    1.15
    >({
    1.10
     {"
    1.08
     ({
    1.07
    ({'
    1.06
     {
    1.05
    :{
    1.05
     ={
    1.02
    Activations Density 0.319%

    No Known Activations