© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9080
    Prev
    Next
    INDEX
    Explanations

    technical definitions and classifications in scientific text

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

    Follows "Co" or similar variants

    np_acts-logits-general · gemini-2.0-flash

    words starting with Co or Ko

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     صوتيه
    -0.60
    ashita
    -0.49
    GEBURTS
    -0.49
    parsedMessage
    -0.49
    XmlAccessorType
    -0.45
    ftagPool
    -0.44
    ьаж
    -0.44
    RegressionTest
    -0.44
     Kinn
    -0.44
     Wul
    -0.42
    POSITIVE LOGITS
     Co
    2.65
    Co
    2.55
     co
    2.48
    co
    2.37
     CO
    2.27
    CO
    2.10
     Ko
    1.82
     코
    1.82
    Ko
    1.78
     ko
    1.77
    Activations Density 0.748%

    No Known Activations