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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9995
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in sentence structures

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

    German and English grammar/syntax

    np_acts-logits-general · gemini-2.0-flash

    adverbial conjunctions and Turkish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.65
    GEBURTSDATUM
    -0.54
    ://$
    -0.52
    Personendaten
    -0.52
    CppMethod
    -0.52
    >
    -0.51
    Datuak
    -0.51
    ()==
    -0.47
    nominal
    -0.47
    endpush
    -0.47
    POSITIVE LOGITS
     unfortunately
    0.74
     nevertheless
    0.60
     sadly
    0.59
     usually
    0.59
     aslında
    0.57
     artık
    0.57
    unfortunately
    0.57
     typically
    0.57
     apparently
    0.56
     ironically
    0.56
    Activations Density 0.203%

    No Known Activations