© 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. 18-GEMMASCOPE-RES-16K
    11. 2191
    Prev
    Next
    INDEX
    Explanations

    references to specific days or notable events

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

    following "one" or "a"

    np_acts-logits-general · gemini-2.0-flash

    one day and a

    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
    dónde
    -0.49
     enci
    -0.42
    setDo
    -0.38
    DataAnnotations
    -0.37
    щами
    -0.37
     tonel
    -0.37
    рек
    -0.36
    شكرا
    -0.36
    uter
    -0.35
    éndolo
    -0.35
    POSITIVE LOGITS
     evening
    1.33
     mornings
    1.30
     afternoon
    1.26
     morning
    1.25
     evenings
    1.24
     afternoons
    1.20
     nights
    1.17
     night
    1.15
     day
    1.13
     summers
    1.08
    Activations Density 0.125%

    No Known Activations