© 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. 24-GEMMASCOPE-RES-16K
    11. 10252
    Prev
    Next
    INDEX
    Explanations

    terms related to immune systems and their functions

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

    relating to systems or economies

    np_acts-logits-general · gemini-2.0-flash

    economy, system, market

    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
     CANCEL
    -0.46
    cancelled
    -0.45
     cancelled
    -0.44
    ToAction
    -0.43
    specialchars
    -0.43
     cancels
    -0.42
     guer
    -0.42
     sticker
    -0.42
    Tages
    -0.42
     Dutch
    -0.42
    POSITIVE LOGITS
     systeem
    0.56
     systému
    0.47
    новништво
    0.45
     podmín
    0.45
     sistema
    0.45
     '\\;'
    0.45
     kokona
    0.45
     verbinding
    0.44
     omgeving
    0.44
    cosystem
    0.44
    Activations Density 1.462%

    No Known Activations