Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11769
    Prev
    Next
    INDEX
    Explanations

    days of the week and specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.96
     nakalista
    -0.90
    GEBURTSDATUM
    -0.86
     فريبيس
    -0.82
    contentLoaded
    -0.81
    SharedDtor
    -0.78
    uxxxx
    -0.74
     חיצוניים
    -0.72
    dafx
    -0.72
    Билгалдахарш
    -0.71
    POSITIVE LOGITS
    ,
    0.56
     Lehmann
    0.46
     متعلقه
    0.46
     bent
    0.45
     milagro
    0.42
    сунок
    0.42
     (
    0.41
    lsb
    0.40
     лицом
    0.40
     nhiên
    0.39
    Activations Density 0.069%

    No Known Activations