© 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. 16-GEMMASCOPE-RES-16K
    6. 9783
    Prev
    Next
    INDEX
    Explanations

    specific metrics related to building size and capacity

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

    Numbers, especially zero

    np_acts-logits-general · gemini-2.0-flash

    acres or square feet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Generale
    -0.70
     fufficient
    -0.70
     Theſe
    -0.69
     BorderRadius
    -0.68
     Majefty
    -0.67
     Efq
    -0.67
    licazione
    -0.66
     Reichstag
    -0.64
    #+#
    -0.64
    PARATOR
    -0.63
    POSITIVE LOGITS
    Offic
    0.47
    kort
    0.44
    //*[@
    0.41
    handel
    0.40
     ince
    0.39
    slidesToShow
    0.39
     acre
    0.39
    INTAIN
    0.38
    Over
    0.38
    なく
    0.38
    Activations Density 0.118%

    No Known Activations