© 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. 24-GEMMASCOPE-RES-16K
    11. 10083
    Prev
    Next
    INDEX
    Explanations

    phrases that point out reasons or explanations for statements

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

    Tokens preceding pronouns or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and pronouns

    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
     więc
    -0.62
     therefore
    -0.61
     however
    -0.59
     donc
    -0.57
     daarom
    -0.54
    therefore
    -0.54
     però
    -0.52
    Therefore
    -0.50
     zatem
    -0.49
     entanto
    -0.49
    POSITIVE LOGITS
     ujednoznacz
    0.42
    gebraucht
    0.40
     possession
    0.40
    SequentialGroup
    0.38
    Personendaten
    0.37
    ⓧ
    0.37
     fileSize
    0.35
     autorytatywna
    0.35
    Filmo
    0.35
     ivelany
    0.35
    Activations Density 0.568%

    No Known Activations