© 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. 18-GEMMASCOPE-RES-16K
    11. 15044
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence or quantity of items or concepts

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

    "are" followed by quantity words

    np_acts-logits-general · gemini-2.0-flash

    existence and quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.82
     ویکی‌پدی
    -0.68
     verksamhet
    -0.65
    prepareStatement
    -0.61
    seamnă
    -0.61
     dovrebbero
    -0.60
     OFDb
    -0.59
     peony
    -0.59
    IndentedString
    -0.59
     dumne
    -0.58
    POSITIVE LOGITS
     many
    1.19
     several
    1.04
     numerous
    0.99
     few
    0.86
     some
    0.84
     plenty
    0.84
     MANY
    0.79
     lots
    0.79
     banyak
    0.77
    several
    0.73
    Activations Density 0.089%

    No Known Activations