© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11938
    Prev
    Next
    INDEX
    Explanations

    references to time-related details, such as days and weeks, in the context of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.72
    TagMode
    -0.54
    LookAnd
    -0.54
     intptr
    -0.50
    来年
    -0.46
    saraba
    -0.46
    SharedDtor
    -0.46
    KURZBESCHREIBUNG
    -0.46
     годах
    -0.45
    ValueStyle
    -0.45
    POSITIVE LOGITS
     week
    3.11
    week
    2.58
     Week
    2.53
    Week
    2.47
     WEEK
    2.34
     weeks
    2.17
     semana
    2.14
     Woche
    2.13
    WEEK
    2.09
     semaine
    2.03
    Activations Density 0.696%

    No Known Activations