© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11339
    Prev
    Next
    INDEX
    Explanations

    phrases expressing honesty or authenticity

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

    following "to be" expressing honesty/fairness

    np_acts-logits-general · gemini-2.0-flash

    to be honest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.60
    хьтан
    -0.53
    RenderAtEndOf
    -0.49
    numerusform
    -0.47
    newtheorem
    -0.47
     @"/
    -0.47
    yntaxException
    -0.46
    verwijspagina
    -0.45
    LEncoder
    -0.45
     ExecuteAsync
    -0.45
    POSITIVE LOGITS
     honestly
    2.22
     frankly
    1.94
    honestly
    1.84
     Honestly
    1.81
     truth
    1.77
    Honestly
    1.75
     tbh
    1.73
     honest
    1.63
     truthfully
    1.62
    Frankly
    1.61
    Activations Density 0.270%

    No Known Activations