© 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. 6275
    Prev
    Next
    INDEX
    Explanations

    phrases involving partnerships or collaborations

    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
    anyway
    -0.42
     anyway
    -0.41
     quelconque
    -0.38
     Anyway
    -0.37
    Anyway
    -0.35
    السكان
    -0.33
     namelijk
    -0.33
     című
    -0.32
     že
    -0.31
    而是
    -0.31
    POSITIVE LOGITS
     emphasis
    1.07
     Emphasis
    0.84
    Emphasis
    0.83
     énfasis
    0.75
     implications
    0.74
    emphasis
    0.73
     plenty
    0.73
     occasional
    0.72
     surla
    0.72
     attendant
    0.70
    Activations Density 0.302%

    No Known Activations