© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9836
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with specific conditions and classifications in a medical or scientific context

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

    ending in "i" followed by additional characters

    np_acts-logits-general · gemini-2.0-flash

    tax system, gaussiani, hamiltonian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    ness
    -0.59
    škas
    -0.53
    çons
    -0.50
     habet
    -0.50
     metų
    -0.50
    kapnya
    -0.44
    ṅ
    -0.44
    ụng
    -0.43
    OGRAPH
    -0.43
     uova
    -0.43
    POSITIVE LOGITS
    SSI
    0.87
    STI
    0.86
    eri
    0.86
    SDI
    0.83
    GRI
    0.82
     SSI
    0.82
     STI
    0.81
    hci
    0.81
    TI
    0.81
     Lori
    0.81
    Activations Density 1.100%

    No Known Activations