© 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. 35-GEMMASCOPE-RES-16K
    11. 8825
    Prev
    Next
    INDEX
    Explanations

    conversations involving requests or instructions about communication and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minangkabau
    -0.34
     joaat
    -0.33
     nordrhein
    -0.32
     referirse
    -0.31
     industrielle
    -0.30
     weib
    -0.30
    płat
    -0.30
     tapis
    -0.30
     reference
    -0.29
     Gebäude
    -0.29
    POSITIVE LOGITS
     Dad
    2.11
     Mom
    2.09
     mom
    2.06
     dad
    2.03
    Dad
    2.02
    Mom
    2.00
     Mum
    1.86
     mommy
    1.85
     Mommy
    1.82
     Daddy
    1.80
    Activations Density 0.480%

    No Known Activations