© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in programming or mathematical text

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

    Code or markup language fragments

    np_acts-logits-general · gemini-2.0-flash

    selective targeting position

    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
     or
    -0.60
     and
    -0.52
    iness
    -0.49
    áním
    -0.48
     a
    -0.47
     called
    -0.44
    fatter
    -0.44
    ularis
    -0.44
    INESS
    -0.43
     certainly
    -0.43
    POSITIVE LOGITS
    ьаж
    1.02
    enderror
    0.89
     NSCoder
    0.85
    AccessorTable
    0.84
    endregion
    0.83
     سكانية
    0.81
     cherchés
    0.79
    IntoConstraints
    0.79
     بيها
    0.78
     pinulongan
    0.75
    Activations Density 0.329%

    No Known Activations