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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5283
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and elements in programming or mathematical expressions

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

    Mathematical or chemical notations and equations

    np_acts-logits-general · gemini-2.0-flash

    chemical formulas with charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     transfieras
    -0.87
     betweenstory
    -0.83
    Autoritní
    -0.80
     kaarangay
    -0.73
     propOrder
    -0.71
     Roskov
    -0.68
    RTEE
    -0.68
     TextAlign
    -0.67
    GEBURTSDATUM
    -0.67
     ویکی‌پدی
    -0.65
    POSITIVE LOGITS
     Komunikasi
    0.39
     uș
    0.35
     Moscú
    0.35
     Kasus
    0.34
     Polres
    0.34
    class
    0.33
     rač
    0.32
    Referencer
    0.32
     bâtiments
    0.31
     missão
    0.31
    Activations Density 0.219%

    No Known Activations