© 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. 33-GEMMASCOPE-RES-16K
    11. 13037
    Prev
    Next
    INDEX
    Explanations

    sentences related to political tactics and hypocrisy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consape
    -0.54
     IMHO
    -0.44
     dürfte
    -0.44
     IMO
    -0.43
    Recognition
    -0.42
    屓
    -0.41
    可以说
    -0.41
     reconoci
    -0.40
     riconos
    -0.40
     recognising
    -0.40
    POSITIVE LOGITS
     somehow
    1.05
     яко
    0.81
     supposedly
    0.74
     magically
    0.71
     angeb
    0.71
     Somehow
    0.71
     superior
    0.70
     inferior
    0.65
    Somehow
    0.63
     allegedly
    0.59
    Activations Density 1.114%

    No Known Activations