© 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. 1302
    Prev
    Next
    INDEX
    Explanations

    references to vector spaces and related concepts in mathematics

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

    "vector" followed by a related term

    np_acts-logits-general · gemini-2.0-flash

    vector-related mathematical and programming terms

    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
    fml
    -0.58
    mergeFrom
    -0.56
    Obrázky
    -0.56
    WebVitals
    -0.54
    LabelTagHelper
    -0.54
    INDUSTRY
    -0.51
    ataire
    -0.50
     Gallimard
    -0.50
     Mish
    -0.50
     Terme
    -0.50
    POSITIVE LOGITS
    stdc
    0.75
     Vectors
    0.73
    ized
    0.71
    AccessorTable
    0.69
    ial
    0.65
    ing
    0.64
    Vectors
    0.63
    Xd
    0.60
     vec
    0.59
     vectors
    0.58
    Activations Density 0.117%

    No Known Activations