© 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. 40-GEMMASCOPE-RES-16K
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    terms related to diagnostics and evaluations in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.60
    ImageContext
    -0.46
     gynhyrchwyd
    -0.44
     &___
    -0.40
    protoimpl
    -0.37
    WithIOException
    -0.36
    Espèce
    -0.36
     نمی
    -0.36
    nehin
    -0.36
    ocino
    -0.35
    POSITIVE LOGITS
     can
    3.48
    can
    2.16
    Can
    1.90
     Can
    1.88
    可以
    1.77
     kann
    1.72
     können
    1.71
     можно
    1.66
     dapat
    1.65
     pouvez
    1.65
    Activations Density 2.913%

    No Known Activations