© 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. 1-GEMMASCOPE-RES-16K
    11. 8999
    Prev
    Next
    INDEX
    Explanations

    references to specific months, particularly May

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.79
     Nuss
    -0.62
    BibitemShut
    -0.62
    crí
    -0.59
     surla
    -0.58
     Dorf
    -0.57
    truc
    -0.56
    arate
    -0.55
     truco
    -0.55
     Scherer
    -0.55
    POSITIVE LOGITS
     May
    4.07
    May
    3.92
    MAY
    2.77
     MAY
    2.53
     maggio
    1.99
    may
    1.91
     April
    1.84
     June
    1.73
     Apr
    1.73
    April
    1.72
    Activations Density 0.073%

    No Known Activations