© 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. 1922
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical spaces and their conditions

    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
    OGND
    -0.52
    AndEndTag
    -0.48
    httphttps
    -0.43
     nahilalakip
    -0.42
    reactstrap
    -0.40
    pædia
    -0.40
    zijde
    -0.39
    MIDDLEWARE
    -0.39
     Ned
    -0.39
    StructEnd
    -0.38
    POSITIVE LOGITS
     floor
    2.09
     flooring
    1.89
     Floor
    1.86
     FLOOR
    1.83
     floors
    1.83
    Floor
    1.79
    floor
    1.76
     carpet
    1.63
    FLOOR
    1.58
     Floors
    1.57
    Activations Density 0.218%

    No Known Activations