© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 352
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnosis, evaluation, and assessment processes

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

    ending in "-tion", "-sis", "-tic", or "-ment"

    np_acts-logits-general · gemini-2.0-flash

    diagnosis, evaluation, analysis, monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.62
    WriteTagHelper
    -0.57
     Picchu
    -0.56
    ifoli
    -0.55
    ClientRect
    -0.52
     invokingState
    -0.51
     Archiproducts
    -0.50
    awaiter
    -0.50
    PreferredItem
    -0.49
    Ӕ
    -0.49
    POSITIVE LOGITS
     methods
    0.45
     efforts
    0.41
     devices
    0.41
     purposes
    0.40
     EconPapers
    0.38
     tasks
    0.37
     tools
    0.37
     schemes
    0.36
     device
    0.36
    ISupport
    0.36
    Activations Density 1.383%

    No Known Activations