© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6346
    Prev
    Next
    INDEX
    Explanations

    details about housing and accommodations

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

    Describes desirable features

    np_acts-logits-general · gemini-2.0-flash

    describing features of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.55
     boîtier
    -0.48
    xffffffff
    -0.48
     imóvel
    -0.48
    voja
    -0.46
     culturale
    -0.46
    swatch
    -0.45
     auszu
    -0.45
     yapı
    -0.45
     metadata
    -0.45
    POSITIVE LOGITS
     plenty
    0.82
     ample
    0.80
     hardwood
    0.73
    Xna
    0.72
     spacious
    0.71
     private
    0.69
     beautiful
    0.69
    '):
    
    0.68
     محفوظة
    0.68
     nice
    0.68
    Activations Density 0.075%

    No Known Activations