© 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. 37-GEMMASCOPE-RES-16K
    11. 7147
    Prev
    Next
    INDEX
    Explanations

    details related to measurements and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρισσότε
    -0.29
    berday
    -0.24
    setLayout
    -0.24
     LinkedList
    -0.23
    SourceChecksum
    -0.23
    velocityY
    -0.23
    はこちら
    -0.22
    就连
    -0.22
    unshift
    -0.21
    setLength
    -0.21
    POSITIVE LOGITS
     about
    2.53
     approximately
    2.30
    about
    2.23
    About
    2.14
     approx
    2.06
     około
    2.03
    approximately
    2.03
     About
    2.02
     aproximadamente
    2.02
     примерно
    1.98
    Activations Density 1.962%

    No Known Activations