© 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. 27-GEMMASCOPE-RES-16K
    11. 11509
    Prev
    Next
    INDEX
    Explanations

    actions and reactions associated with deception and surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shimizu
    -0.45
     Leib
    -0.43
     getir
    -0.42
    tôi
    -0.41
    edicated
    -0.41
     Reve
    -0.40
    libft
    -0.40
     Nguyên
    -0.40
     Opt
    -0.39
     Zing
    -0.39
    POSITIVE LOGITS
     linkovi
    0.48
    aarrggbb
    0.47
     kasarigan
    0.44
    IntoConstraints
    0.42
    MeasureSpec
    0.41
    upon
    0.40
    
    0.39
     dealt
    0.39
     '\\;'
    0.39
    Хьажоргаш
    0.38
    Activations Density 0.203%

    No Known Activations