© 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. 11-GEMMASCOPE-RES-16K
    6. 8430
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials and research methodologies in neuroscience and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    foreach
    -0.46
    */
    
    
    -0.45
     Felic
    -0.45
     Katar
    -0.44
     ujednoznacz
    -0.43
    import
    -0.42
    HIND
    -0.42
    Katar
    -0.42
    Fig
    -0.41
    mH
    -0.41
    POSITIVE LOGITS
    Datuak
    0.65
    Autoritní
    0.62
    LEGGI
    0.61
    SharedDtor
    0.60
     abstrato
    0.60
     digitais
    0.60
     Municipalidad
    0.59
     Bulls
    0.58
    ratios
    0.58
    AutoScaleMode
    0.57
    Activations Density 2.851%

    No Known Activations