© 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. 14524
    Prev
    Next
    INDEX
    Explanations

    references to political and legal terminology

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

    German or partially German words

    np_acts-logits-general · gemini-2.0-flash

    Speicher, Blankenfelde, Bornhöved

    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
     Cæsar
    -0.44
     Diſ
    -0.42
    fill
    -0.42
    ÓS
    -0.42
     Hadrian
    -0.39
     Fulda
    -0.39
     Must
    -0.39
     Verdad
    -0.39
    mena
    -0.38
     Græ
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.91
    LLocation
    0.84
     Roskov
    0.83
     MenuView
    0.77
    GEBURTSDATUM
    0.74
     lenker
    0.73
     InputDecoration
    0.73
     StatefulWidget
    0.72
    ltä
    0.71
     BoxDecoration
    0.71
    Activations Density 0.045%

    No Known Activations