© 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. 15-GEMMASCOPE-RES-16K
    11. 1980
    Prev
    Next
    INDEX
    Explanations

    temporal references and phrases indicating specific periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delige
    -0.61
    eseorang
    -0.55
    DialogContent
    -0.55
    gino
    -0.55
     giornal
    -0.51
    Cordialement
    -0.51
     financières
    -0.49
     tendre
    -0.48
    存于互联网档案馆
    -0.48
     coscienza
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.63
    InstrumentedTest
    0.63
     تكبرها
    0.61
     unknownFields
    0.60
    Personendaten
    0.57
     שוליים
    0.56
    +:+
    0.53
     disambiguazione
    0.52
     invokingState
    0.52
    못
    0.52
    Activations Density 0.237%

    No Known Activations