© 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. 9492
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific analysis and composition, particularly within a biological or chemical context

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

    Numerical values of physical or chemical properties

    np_acts-logits-general · gemini-2.0-flash

    physical properties and values

    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
     Lightboxes
    -0.64
     himſelf
    -0.60
    barui
    -0.60
     XNUMX
    -0.55
     incredibly
    -0.54
    VINCE
    -0.54
     gouver
    -0.54
    setCharacter
    -0.54
    mergeFrom
    -0.53
     ſeveral
    -0.52
    POSITIVE LOGITS
    upto
    1.06
     upto
    1.05
     viz
    0.90
    Contd
    0.87
     atleast
    0.82
    
    0.80
     judicious
    0.74
    viz
    0.71
    contd
    0.71
     contd
    0.70
    Activations Density 0.427%

    No Known Activations