© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    details related to scientific methods and processes, particularly in biological and chemical experiments

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

    numbers and units

    np_acts-logits-general · gemini-2.0-flash

    quantities and measurements

    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
    İstinadlar
    -0.61
    Hozzáférés
    -0.53
     Именно
    -0.50
     незавершена
    -0.47
    jface
    -0.46
    LEncoder
    -0.45
    ournal
    -0.45
    casian
    -0.45
     W
    -0.45
    wości
    -0.43
    POSITIVE LOGITS
     amounting
    1.08
     totalling
    1.05
     totaling
    1.05
     numbering
    1.00
     sebesar
    0.87
     averaging
    0.83
     snippetHide
    0.80
     ranging
    0.77
     âgé
    0.76
     eighteen
    0.76
    Activations Density 1.321%

    No Known Activations