© 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. 4462
    Prev
    Next
    INDEX
    Explanations

    terms related to signals and their detection or processing

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

    "signal"

    np_acts-logits-general · gemini-2.0-flash

    signal detection, application, and processing

    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
    edos
    -0.61
    findpost
    -0.60
    verifyException
    -0.55
    ecma
    -0.55
    StoryboardSegue
    -0.54
    ly
    -0.54
    ΗΣ
    -0.52
     Fuß
    -0.52
    ungere
    -0.50
    rawDesc
    -0.50
    POSITIVE LOGITS
     Signals
    0.94
     signals
    0.92
    signals
    0.91
    Signals
    0.82
    FormTagHelper
    0.80
     Sauer
    0.69
     Signal
    0.68
    addPreferredGap
    0.67
     SIG
    0.65
    SIGNAL
    0.64
    Activations Density 0.141%

    No Known Activations