© 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. 12-GEMMASCOPE-RES-16K
    11. 8394
    Prev
    Next
    INDEX
    Explanations

    informal expressions and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     praktijk
    -0.42
     villaggio
    -0.38
     lettore
    -0.36
     pengguna
    -0.36
     mempel
    -0.35
     contrário
    -0.35
     użytk
    -0.35
     vrijwilli
    -0.34
     nødven
    -0.34
    ese
    -0.33
    POSITIVE LOGITS
     dudes
    0.78
     dude
    0.74
     dope
    0.66
    dope
    0.65
     homie
    0.65
     swagger
    0.60
     swag
    0.60
     transfieras
    0.60
     badass
    0.59
     motherfucker
    0.59
    Activations Density 0.666%

    No Known Activations