© 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. 16-GEMMASCOPE-RES-16K
    11. 13248
    Prev
    Next
    INDEX
    Explanations

    the presence of headings or structured sections in text

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

    Text following colons or beginning code blocks

    np_acts-logits-general · gemini-2.0-flash

    questions and technical terms

    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
    ณ์
    -0.61
    Coordenadas
    -0.59
     optimised
    -0.59
    enumi
    -0.56
     bambu
    -0.54
     Traducción
    -0.54
    MOTION
    -0.53
     optimisation
    -0.52
     probably
    -0.52
    ichter
    -0.52
    POSITIVE LOGITS
    Jsp
    0.57
    #+#
    0.56
     كورة
    0.55
     ThemeData
    0.54
     NSObject
    0.54
     QWidget
    0.54
     QString
    0.53
    Witam
    0.50
    PreferredItem
    0.49
    dafx
    0.49
    Activations Density 0.015%

    No Known Activations