© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8804
    Prev
    Next
    INDEX
    Explanations

    temporal words and phrases indicating time relationships or sequences of events

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

    that come before or after time periods

    np_acts-logits-general · gemini-2.0-flash

    before events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.75
     normaux
    -0.74
     Houſe
    -0.69
     Monfieur
    -0.65
     quæ
    -0.59
     sandero
    -0.58
     houſe
    -0.57
    िखित
    -0.57
     tué
    -0.56
     lyon
    -0.56
    POSITIVE LOGITS
    tvguidetime
    0.78
    Datuak
    0.70
     '{@
    0.70
     سكانية
    0.64
     calendriers
    0.64
     its
    0.63
    :][
    0.61
     TextAppearance
    0.60
    )="
    0.60
    ocino
    0.59
    Activations Density 0.169%

    No Known Activations