© 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. 8975
    Prev
    Next
    INDEX
    Explanations

    numerical dates and event-related details

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

    Prepositions and punctuation

    np_acts-logits-general · gemini-2.0-flash

    funeral arrangements

    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
    béco
    -0.53
     Guiana
    -0.48
    dyna
    -0.43
    expandindo
    -0.42
     budgets
    -0.42
     Guyana
    -0.41
    espé
    -0.41
     pourtant
    -0.41
     fig
    -0.41
    ᵎ
    -0.41
    POSITIVE LOGITS
     offici
    0.62
    ModelSerializer
    0.58
     Interment
    0.55
     suivie
    0.55
    TypedDataSet
    0.54
     interment
    0.51
     attendees
    0.50
     funeral
    0.50
     followed
    0.50
     graves
    0.47
    Activations Density 0.009%

    No Known Activations