© 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. 3-GEMMASCOPE-RES-16K
    11. 9887
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "up"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.56
     Monfieur
    -0.55
     safer
    -0.54
     Majefty
    -0.53
    ()].
    -0.52
     bodem
    -0.50
    ebenarnya
    -0.50
    eseorang
    -0.50
     myſelf
    -0.48
     voici
    -0.48
    POSITIVE LOGITS
    expandindo
    0.68
    出版年
    0.66
    kwds
    0.65
    SharedDtor
    0.60
    DECREF
    0.60
    OrBuilder
    0.60
    findpost
    0.59
    fromCharCode
    0.59
    stds
    0.58
     QtWidgets
    0.58
    Activations Density 0.325%

    No Known Activations