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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14711
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical user interface components and structure in code

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

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    end of statement or block

    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
     fieldNum
    -0.71
    <bos>
    -0.70
    cshtml
    -0.68
    offsetof
    -0.65
     @"/
    -0.60
    */].
    -0.56
    StructEnd
    -0.55
     Vian
    -0.55
    nodoc
    -0.54
    AddTagHelper
    -0.53
    POSITIVE LOGITS
    èdia
    0.63
     Normdatei
    0.62
     متعلقه
    0.61
     protoimpl
    0.60
     ſhe
    0.59
     obſ
    0.59
     ſaid
    0.57
     Waray
    0.57
     débil
    0.57
     FBref
    0.54
    Activations Density 0.118%

    No Known Activations