© 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. 2-GEMMASCOPE-RES-16K
    11. 6536
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.50
    Xna
    -0.46
     jama
    -0.45
    jší
    -0.43
    inata
    -0.43
     Pasteur
    -0.42
     TextInput
    -0.42
     SqlParameter
    -0.41
     indian
    -0.41
    bonne
    -0.41
    POSITIVE LOGITS
     says
    2.52
    says
    2.09
     Says
    1.92
    Says
    1.91
     SAYS
    1.68
     zegt
    1.55
     говорит
    1.28
     sagt
    1.25
     säger
    1.24
     sanoo
    1.22
    Activations Density 0.179%

    No Known Activations