© 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 EvalsExportsAPI 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. 10474
    Prev
    Next
    INDEX
    Explanations

    terms related to "bore" and "Borel," indicating a focus on mathematical concepts and terminology

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

    ending in "ore," "ure," or "son."

    np_acts-logits-general · gemini-2.0-flash

    Borel, ore, Aure, Arena, Sorenson

    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
    ‍♀️
    -0.52
    InstanceId
    -0.51
    wiss
    -0.49
     anf
    -0.48
    ICK
    -0.46
    itons
    -0.46
    atk
    -0.46
    itäts
    -0.46
    felf
    -0.46
    IPLE
    -0.46
    POSITIVE LOGITS
    DataMember
    0.53
    featureID
    0.53
    didSet
    0.51
     feroit
    0.49
     odpowiedzial
    0.49
     meille
    0.47
     morrer
    0.46
    lardır
    0.46
     esclavos
    0.46
     geweest
    0.45
    Activations Density 0.592%

    No Known Activations