© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    words related to identity and recognition within relationships

    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
     AssemblyTitle
    -0.48
    RectangleBorder
    -0.46
    apimachinery
    -0.45
    ESTAMP
    -0.45
    chyma
    -0.44
     denture
    -0.44
     endwhile
    -0.43
     GenerationType
    -0.42
     FishBase
    -0.42
    menuStrip
    -0.42
    POSITIVE LOGITS
    Joc
    0.65
    zok
    0.63
     Jog
    0.63
     IOC
    0.62
     Jodie
    0.61
    xox
    0.61
    OGND
    0.60
     Voss
    0.60
    jot
    0.59
     Jot
    0.59
    Activations Density 0.950%

    No Known Activations