© 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. 24-GEMMASCOPE-RES-16K
    11. 12259
    Prev
    Next
    INDEX
    Explanations

    technical jargon and specific programming concepts related to software development

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

    Strings or identifiers

    np_acts-logits-general · gemini-2.0-flash

    code comments and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.61
    expandindo
    -0.57
    FXML
    -0.57
    __*/
    -0.55
     تعدى
    -0.53
    
    -0.53
     createState
    -0.53
    MessageOf
    -0.53
     LUMP
    -0.52
    emeni
    -0.52
    POSITIVE LOGITS
     Assumption
    0.55
    cioc
    0.51
    psack
    0.50
    Spes
    0.48
    Inspired
    0.48
     Schwal
    0.47
     Ausblick
    0.46
    Assumption
    0.46
     Inspired
    0.46
    windowFixed
    0.45
    Activations Density 0.113%

    No Known Activations