© 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. 15-GEMMASCOPE-RES-16K
    11. 2052
    Prev
    Next
    INDEX
    Explanations

    nested structures and organization in data formats like JSON or programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.44
     av
    -0.35
    ↵↵
    -0.35
    companion
    -0.33
    Gost
    -0.32
    final
    -0.31
     Gost
    -0.31
    مراجع
    -0.31
     uitz
    -0.30
     incluida
    -0.30
    POSITIVE LOGITS
    outSlope
    0.67
    AccessorTable
    0.64
     kasarigan
    0.63
     Numerade
    0.60
    makeText
    0.59
     CURIAM
    0.59
     فريبيس
    0.59
    AddTagHelper
    0.58
     StatefulWidget
    0.58
    principalColumn
    0.57
    Activations Density 0.372%

    No Known Activations