© 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. 22-GEMMASCOPE-RES-16K
    11. 7338
    Prev
    Next
    INDEX
    Explanations

    code-related terms and methods, particularly involving fetching and processing data from APIs

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

    Code snippets or programming terms

    np_acts-logits-general · gemini-2.0-flash

    code and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()
    -1.45
    ();
    -1.28
    (),
    -1.22
    ());
    -1.20
     ()
    -1.16
    ())
    -1.15
    ()",
    -1.13
    ():
    -1.12
    (){
    -1.12
    ().
    -1.10
    POSITIVE LOGITS
     snippetHide
    0.73
     ostavi
    0.65
    Portail
    0.65
     المعيارى
    0.65
    AddTagHelper
    0.64
    پیوند
    0.64
     للمعارف
    0.64
    ~(
    0.63
     (
    0.63
    참고
    0.62
    Activations Density 0.274%

    No Known Activations