© 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. 1-GEMMASCOPE-RES-16K
    11. 11124
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "already."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lwz
    -0.49
    rangian
    -0.44
     trụ
    -0.44
     <=",
    -0.42
     convient
    -0.39
    TRS
    -0.38
     predicated
    -0.37
     geographical
    -0.36
     snare
    -0.35
     갈
    -0.35
    POSITIVE LOGITS
     already
    0.97
     Already
    0.92
    Already
    0.88
    already
    0.85
     ALREADY
    0.83
     noticed
    0.78
    ALREADY
    0.69
     déjà
    0.68
     noticing
    0.68
     уже
    0.68
    Activations Density 0.276%

    No Known Activations