© 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. 31-GEMMASCOPE-RES-16K
    11. 7185
    Prev
    Next
    INDEX
    Explanations

    references to SA (presumably a specific term or entity) and related classifications

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

    two-character sequences or abbreviations beginning with "Sa" or "SA".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stadig
    -0.42
    landır
    -0.41
    MENAFN
    -0.40
     censiti
    -0.39
     AssemblyCulture
    -0.38
     copos
    -0.36
     kèm
    -0.35
     üzere
    -0.34
    <h5>
    -0.34
    Particular
    -0.34
    POSITIVE LOGITS
    хьтан
    0.61
     Sa
    0.52
    Хьажоргаш
    0.48
     kasarigan
    0.48
     onPostExecute
    0.48
    IsContent
    0.47
     saver
    0.47
    Sa
    0.47
     Saver
    0.47
     contextLoads
    0.44
    Activations Density 0.322%

    No Known Activations