© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    words related to objects being secured or attached

    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
    Dış
    -0.37
     picioare
    -0.35
     kapcsolat
    -0.33
     fapt
    -0.31
    nisses
    -0.31
     popoli
    -0.30
    zlich
    -0.30
     pregunto
    -0.30
    ſelves
    -0.30
     åt
    -0.29
    POSITIVE LOGITS
    DockStyle
    0.72
     wall
    0.71
     walls
    0.69
    Kjelder
    0.69
    RegressionTest
    0.68
    queryInterface
    0.68
    walls
    0.66
    wall
    0.64
     Taktlose
    0.63
    Хьажоргаш
    0.60
    Activations Density 0.609%

    No Known Activations