© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82334
    Prev
    Next
    INDEX
    Explanations

    terms expressing contradiction or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nevertheless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.71
     Himo
    -0.64
    
    -0.60
    AndEndTag
    -0.60
    OuterAlt
    -0.58
     kasarigan
    -0.58
    llary
    -0.56
     kaarangay
    -0.54
    IntoConstraints
    -0.54
    Aid
    -0.52
    POSITIVE LOGITS
    却
    1.96
    卻
    1.80
    但却
    1.23
    却不
    1.20
    却是
    1.13
    却没有
    1.11
    却被
    1.09
    却又
    1.04
     però
    0.81
     justru
    0.74
    Activations Density 0.002%

    No Known Activations