© 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. 20-GEMMASCOPE-RES-16K
    11. 6268
    Prev
    Next
    INDEX
    Explanations

    specialized terms or symbols commonly used in mathematical or technical contexts

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

    Text within square brackets

    np_acts-logits-general · gemini-2.0-flash

    micro

    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
    AsUp
    -1.28
     <>",
    -1.17
     '\\;'
    -1.16
     NSCoder
    -1.14
    writeFieldEnd
    -1.14
    setVerticalGroup
    -1.11
    SharedDtor
    -1.10
    __':
    -1.09
    تقاوى
    -1.08
    ReusableCell
    -1.04
    POSITIVE LOGITS
    other
    0.63
    ↵↵
    0.61
    no
    0.60
    <eos>
    0.60
    @
    0.57
    <strong>
    0.57
    ↵
    0.57
    (
    0.57
    No
    0.55
    ther
    0.55
    Activations Density 1.427%

    No Known Activations