© 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. 10-GEMMASCOPE-RES-16K
    11. 3145
    Prev
    Next
    INDEX
    Explanations

    locations or contexts where the word "in" appears frequently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neſs
    -0.57
     AssemblyCompany
    -0.57
    PerformLayout
    -0.56
    ⟬
    -0.55
    المناصب
    -0.54
    engertian
    -0.47
    consulté
    -0.46
     myſelf
    -0.46
    eseorang
    -0.45
     Administrativna
    -0.45
    POSITIVE LOGITS
     in
    0.66
     into
    0.57
     inside
    0.52
     occupying
    0.51
     Occupied
    0.50
    dentro
    0.49
     occupy
    0.47
     ocupar
    0.47
     Into
    0.47
     isIn
    0.47
    Activations Density 0.889%

    No Known Activations