© 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. 14942
    Prev
    Next
    INDEX
    Explanations

    references to streams and streaming processes

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

    "stream" and its variations

    np_acts-logits-general · gemini-2.0-flash

    stream and lines/flow/cipher

    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
    ngdoc
    -0.92
    ArgsConstructor
    -0.82
     BoxDecoration
    -0.74
    IUrlHelper
    -0.72
    Amen
    -0.60
     StatelessWidget
    -0.60
    XmlAccessorType
    -0.59
     estimés
    -0.59
     Erişim
    -0.59
    webElementGuid
    -0.58
    POSITIVE LOGITS
    lined
    0.82
    lining
    0.76
    flow
    0.68
    lines
    0.67
    line
    0.63
    flows
    0.62
    streams
    0.61
    gdx
    0.61
    LIN
    0.60
     streams
    0.59
    Activations Density 0.116%

    No Known Activations