© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3715
    Prev
    Next
    INDEX
    Explanations

    references to measurements and dimensions

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

    Dimensions or sizes

    np_acts-logits-general · gemini-2.0-flash

    x followed by numbers or units

    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
     intptr
    -0.73
     otomatig
    -0.72
    SequentialGroup
    -0.68
    endregion
    -0.68
     <<<<<<<<<<<<<<
    -0.67
    Джерела
    -0.65
     initComponents
    -0.63
     linkovi
    -0.63
    TabIndex
    -0.63
    EndContext
    -0.61
    POSITIVE LOGITS
     disambiguazione
    0.61
    whatever
    0.60
    writerow
    0.56
    Whatever
    0.53
    eddable
    0.53
     plunger
    0.52
    لاعات
    0.52
     Whatever
    0.52
     Anybody
    0.51
    pkey
    0.51
    Activations Density 0.762%

    No Known Activations