© 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. 40-GEMMASCOPE-RES-16K
    11. 7071
    Prev
    Next
    INDEX
    Explanations

    emphasized words or phrases, possibly indicating importance or focus in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totalidad
    -0.42
     dozen
    -0.38
     dozens
    -0.36
    million
    -0.35
     cuarta
    -0.34
     million
    -0.34
    twelve
    -0.33
     hundred
    -0.32
     millón
    -0.32
     cincuenta
    -0.31
    POSITIVE LOGITS
     nahilalakip
    0.87
     فريبيس
    0.66
    enumii
    0.58
    windowFixed
    0.57
    Хьажоргаш
    0.57
    Autoritní
    0.57
    exitRule
    0.56
    LEGGI
    0.56
     nakalista
    0.55
    rungsseite
    0.54
    Activations Density 0.457%

    No Known Activations