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. 10704
    Prev
    Next
    INDEX
    Explanations

    commands and parameters related to data processing and structure

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

    Code snippets or configuration blocks

    np_acts-logits-general · gemini-2.0-flash

    code options and configuration

    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
    AutoField
    -0.70
     &___
    -0.66
    ⓧ
    -0.60
    CodeAttribute
    -0.60
    EClass
    -0.59
    MemoryWarning
    -0.57
    Xna
    -0.56
     betweenstory
    -0.56
    afficheront
    -0.56
    ReusableCell
    -0.55
    POSITIVE LOGITS
    @@@@@@@@
    0.63
    >-->
    0.57
     action
    0.56
    )";
    
    0.54
    kkar
    0.53
    nología
    0.53
     LXXX
    0.50
    ?')
    0.50
    PRNewswire
    0.50
    ArgumentParser
    0.48
    Activations Density 0.055%

    No Known Activations