© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12506
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to clinical studies and genetic therapies for specific diseases

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

    Lysosomal storage disorders and genetic diseases

    np_acts-logits-general · gemini-2.0-flash

    rare genetic disorders

    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
     wireType
    -0.55
    はじめに
    -0.45
    NameInMap
    -0.44
     uLocal
    -0.41
    Promotion
    -0.40
     camb
    -0.40
    GIVEREF
    -0.38
     mål
    -0.38
    állítás
    -0.38
    COUVER
    -0.37
    POSITIVE LOGITS
     autos
    0.65
     rare
    0.65
     mutation
    0.61
     Autos
    0.61
     hereditary
    0.58
     gene
    0.58
     mutations
    0.57
     defects
    0.56
     defect
    0.55
     Mutations
    0.55
    Activations Density 1.270%

    No Known Activations