© 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. 20-GEMMASCOPE-RES-16K
    11. 15119
    Prev
    Next
    INDEX
    Explanations

    words related to processes or actions pertaining to handling data and systems

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

    Fragments of German or technical language

    np_acts-logits-general · gemini-2.0-flash

    beam lithography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noons
    -0.72
    znym
    -0.58
    Havolalar
    -0.58
    tvguidetime
    -0.54
     zufolge
    -0.54
     eletrônico
    -0.53
    udur
    -0.52
    ofern
    -0.52
     Barran
    -0.51
    twas
    -0.51
    POSITIVE LOGITS
     sich
    0.87
     zich
    0.73
     into
    0.65
     in
    0.55
     on
    0.54
     einen
    0.54
     them
    0.54
     from
    0.52
    એ
    0.51
     את
    0.51
    Activations Density 0.028%

    No Known Activations