© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7165
    Prev
    Next
    INDEX
    Explanations

    references to location and modernity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFields
    -0.59
    adaptiveStyles
    -0.54
    edakan
    -0.54
    IMPORTED
    -0.50
     sẵn
    -0.50
    ysteem
    -0.49
     (!_
    -0.47
     JUGA
    -0.47
    __((
    -0.47
    ânt
    -0.46
    POSITIVE LOGITS
     Heute
    0.65
    ormais
    0.62
    Today
    0.62
    Spoljašnje
    0.60
     âmes
    0.59
     today
    0.59
     myö
    0.58
    today
    0.58
     heutigen
    0.57
     Today
    0.57
    Activations Density 0.469%

    No Known Activations