© 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. 39-GEMMASCOPE-RES-16K
    11. 4196
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and closing brackets, often indicating the end of code blocks or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -0.93
    ())){
    -0.89
    ">
    -0.88
    );
    -0.87
    });
    -0.86
    '}>
    -0.85
    ")){
    -0.84
     }}}{
    -0.84
    ')){
    -0.84
    ();
    -0.83
    POSITIVE LOGITS
     '\\;'
    0.60
    новниш
    0.59
    tagHelperRunner
    0.56
     AppCompatTheme
    0.56
     pleaſure
    0.52
     Reverso
    0.49
    Bissau
    0.49
     ainfi
    0.48
    AddTagHelper
    0.47
     nahilalakip
    0.47
    Activations Density 0.251%

    No Known Activations