© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3629
    Prev
    Next
    INDEX
    Explanations

    increment and decrement operators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nevera
    -0.54
    Obrázky
    -0.52
    Clarke
    -0.48
     Clarke
    -0.46
    Espagne
    -0.46
    ikala
    -0.46
    herme
    -0.46
    nake
    -0.46
     tutors
    -0.45
     pulsera
    -0.45
    POSITIVE LOGITS
    ++)
    0.96
    ++)
    
    0.88
    ++;
    0.80
    ++){
    0.79
    ++,
    0.75
    ++);
    0.69
    ++;
    
    0.66
     ++)
    0.63
     nationwide
    0.62
    ++
    0.61
    Activations Density 0.117%

    No Known Activations