© 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. 7-GEMMASCOPE-RES-16K
    11. 13485
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to suppression or repression, especially in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.58
    iNdEx
    -0.54
    URLException
    -0.53
    ########.
    -0.52
    DockStyle
    -0.51
    SourceChecksum
    -0.47
    SceneManagement
    -0.43
    Gle
    -0.43
     NSCoder
    -0.42
     Meksiku
    -0.42
    POSITIVE LOGITS
     suppression
    1.89
     suppress
    1.87
     suppressed
    1.80
     suppressing
    1.73
     Suppression
    1.70
     suppresses
    1.65
    suppress
    1.44
     suppressor
    1.38
    Suppress
    1.30
     inhibition
    1.30
    Activations Density 0.547%

    No Known Activations