© 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. 12023
    Prev
    Next
    INDEX
    Explanations

    references to social and cultural dynamics, particularly concerning race and heritage

    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
     rehe
    -0.55
     المعيارى
    -0.48
     ujednoznacz
    -0.46
     fours
    -0.46
     timed
    -0.46
     InputDecoration
    -0.45
    pośred
    -0.45
    Visiting
    -0.45
     Visiting
    -0.45
     visiting
    -0.44
    POSITIVE LOGITS
    可谓
    0.52
     highly
    0.51
    highly
    0.49
    yntaxException
    0.47
     disadvantaged
    0.47
     carcinogenic
    0.44
     excellence
    0.44
     laudable
    0.44
     Wegen
    0.43
     ecological
    0.43
    Activations Density 1.676%

    No Known Activations