© 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. 40-GEMMASCOPE-RES-16K
    6. 2530
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and physiological conditions and measurements

    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
    ")){
    
    -0.48
    ']));
    -0.41
    ")));
    
    -0.38
    ']))
    
    -0.38
    "]);
    
    -0.36
    '])){
    -0.36
    }}/>
    -0.35
    ")){
    -0.35
    "))
    
    -0.34
    ')));
    -0.34
    POSITIVE LOGITS
    ation
    0.91
    ated
    0.89
    ers
    0.83
    ating
    0.83
    ous
    0.82
    ity
    0.82
    ing
    0.82
    ations
    0.81
    ted
    0.80
    ate
    0.79
    Activations Density 1.269%

    No Known Activations