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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15359
    Prev
    Next
    INDEX
    Explanations

    references to religious structures and shrines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "St," "of," or "in"

    np_acts-logits-general · gemini-2.0-flash

    saint names or religious figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.54
     Agamemnon
    -0.44
     Midas
    -0.42
     veda
    -0.40
     Indra
    -0.39
     Molière
    -0.38
     Majefty
    -0.38
     pleaſure
    -0.38
    amemnon
    -0.38
    ToProps
    -0.37
    POSITIVE LOGITS
     Virgin
    0.65
    Virgin
    0.64
    virgin
    0.60
    GEBURTSDATUM
    0.58
     virgin
    0.57
     saint
    0.54
     Miracle
    0.53
     patron
    0.52
     ujednoznacz
    0.52
     Blessed
    0.52
    Activations Density 0.142%

    No Known Activations