© 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 EvalsExportsinterp-engineNEWAPI 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. 11459
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the greatest number or majority

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

    Follows the word "most"

    np_acts-logits-general · gemini-2.0-flash

    most

    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
    aryen
    -0.48
     Schild
    -0.47
     Waterloo
    -0.47
    Waterloo
    -0.46
     Ename
    -0.44
     Andersson
    -0.44
     CrossRef
    -0.43
    JNIEnv
    -0.43
     Parallel
    -0.42
     Martel
    -0.42
    POSITIVE LOGITS
     MOST
    0.88
     flesta
    0.81
    most
    0.78
    Most
    0.78
     Most
    0.78
    MOST
    0.78
     maioria
    0.77
     meisten
    0.76
     meeste
    0.74
     plupart
    0.72
    Activations Density 0.086%

    No Known Activations