© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4194
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and biological terms related to proteins and immunology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kirkpatrick
    -0.51
     Hartmann
    -0.46
     Calvo
    -0.45
    menuStrip
    -0.44
     rega
    -0.43
     Leal
    -0.43
    newInstance
    -0.42
     pran
    -0.42
    tagext
    -0.42
    دواج
    -0.42
    POSITIVE LOGITS
    PB
    0.65
    Pb
    0.57
     pb
    0.56
    RefNanny
    0.55
     PB
    0.55
     initComponents
    0.54
    pb
    0.54
     Bambi
    0.53
    CORD
    0.52
     productividad
    0.51
    Activations Density 1.101%

    No Known Activations