© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 13684
    Prev
    Next
    INDEX
    Explanations

    special characters and unusual formatting within the text

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

    Emphasis or sarcasm markers

    np_acts-logits-general · gemini-2.0-flash

    intensifiers and emphasis

    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
    isInitialized
    -0.52
    virons
    -0.51
    putar
    -0.47
    iciary
    -0.47
     Sala
    -0.47
    PERTIES
    -0.46
    FOLK
    -0.46
     medel
    -0.46
    POSE
    -0.45
    writeln
    -0.45
    POSITIVE LOGITS
    تقاوى
    0.96
    ंदीखरीदारी
    0.83
    <em>
    0.82
     definitely
    0.81
    WithIOException
    0.81
     absolutely
    0.76
    <i>
    0.75
    DockStyle
    0.73
     dAtA
    0.73
    ValueStyle
    0.72
    Activations Density 0.184%

    No Known Activations