© 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. 37-GEMMASCOPE-RES-16K
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    keywords related to various biological processes and indicators of health or disease

    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
    ViewImports
    -0.37
     frattempo
    -0.35
     wont
    -0.34
     AttributeSet
    -0.33
     Requires
    -0.33
    GenerationType
    -0.33
     ressemble
    -0.32
    かというと
    -0.31
     looks
    -0.30
    mäß
    -0.30
    POSITIVE LOGITS
     plays
    2.13
     play
    1.98
     played
    1.84
    plays
    1.76
     Plays
    1.75
     playing
    1.64
    Plays
    1.63
    played
    1.58
    play
    1.56
     PLAY
    1.56
    Activations Density 1.445%

    No Known Activations