© 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
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5659
    Prev
    Next
    INDEX
    Explanations

    references to medical assessments and treatments related to headaches

    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
     gynhyrchwyd
    -0.66
    Jeografia
    -0.66
    parsedMessage
    -0.60
    ConstraintMaker
    -0.59
    fromnode
    -0.57
    MessageTagHelper
    -0.54
     nahilalakip
    -0.53
    цездатний
    -0.52
     surla
    -0.51
    NameInMap
    -0.49
    POSITIVE LOGITS
    5
    1.94
    3
    1.93
    6
    1.91
    4
    1.91
    2
    1.91
    1
    1.88
    7
    1.86
    8
    1.84
    9
    1.79
    0
    1.38
    Activations Density 5.012%

    No Known Activations