© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4796
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurements and simulations

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

    Spatial, spectral, or measurement resolution

    np_acts-logits-general · gemini-2.0-flash

    finer resolution, accuracy, precision

    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
    CardHeader
    -0.41
    Rujuakan
    -0.33
     char
    -0.33
     energ
    -0.33
     javafx
    -0.32
     sessions
    -0.32
     total
    -0.32
    QPalette
    -0.31
     Taktlose
    -0.31
    يكب
    -0.31
    POSITIVE LOGITS
     finer
    0.74
     resolution
    0.74
     tiny
    0.70
     Auflösung
    0.69
     smallest
    0.68
    ละเอียด
    0.68
     accuracy
    0.68
    细
    0.67
     precision
    0.64
     feinen
    0.63
    Activations Density 1.113%

    No Known Activations