© 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. 34-GEMMASCOPE-RES-16K
    11. 823
    Prev
    Next
    INDEX
    Explanations

    statements regarding integrity and truthfulness in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -0.51
    حوالہ
    -0.50
    ViewFeatures
    -0.49
    rawDesc
    -0.48
     useCallback
    -0.46
    endphp
    -0.45
    blauch
    -0.45
     noDo
    -0.45
     فريبيس
    -0.45
    Cyfarwyddwr
    -0.44
    POSITIVE LOGITS
     lies
    1.69
     falsehood
    1.66
     mentira
    1.63
     lied
    1.60
     lie
    1.59
     false
    1.57
     mentiras
    1.56
     deception
    1.50
     liars
    1.49
     lying
    1.46
    Activations Density 1.048%

    No Known Activations