© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    responses related to quiz or test answers, particularly false responses and categories

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

    French language related text

    np_acts-logits-general · gemini-2.0-flash

    reponse correcte or fausse

    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
     himself
    -0.77
     który
    -0.62
     који
    -0.60
     який
    -0.59
     который
    -0.59
     koji
    -0.56
     său
    -0.56
    彼は
    -0.55
    彼の
    -0.54
     his
    -0.54
    POSITIVE LOGITS
     herself
    0.79
     she
    0.72
    herself
    0.58
    UserScript
    0.53
     dite
    0.53
     locale
    0.52
     Locale
    0.52
    she
    0.51
    
    0.51
    itative
    0.50
    Activations Density 0.065%

    No Known Activations