© 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. 5638
    Prev
    Next
    INDEX
    Explanations

    phrases related to the development of new methodologies or tools

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

    Follows verbs like "developed," "released," "issued," or "propose"

    np_acts-logits-general · gemini-2.0-flash

    introduce new methods

    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
    bootstrapcdn
    -1.11
    PerformLayout
    -0.99
    RectangleBorder
    -0.94
    AsUp
    -0.93
     Meksiku
    -0.89
     AssemblyCulture
    -0.86
    Portale
    -0.85
    RegressionTest
    -0.85
    IVEREF
    -0.84
    ⓧ
    -0.84
    POSITIVE LOGITS
     a
    0.72
     two
    0.63
     several
    0.60
     an
    0.54
     three
    0.53
     separate
    0.52
     guidelines
    0.51
    izou
    0.47
    zony
    0.46
     detailed
    0.45
    Activations Density 0.441%

    No Known Activations