© 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. 28-GEMMASCOPE-RES-16K
    11. 3193
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and vulnerability

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

    "honest" or "honestly"

    np_acts-logits-general · gemini-2.0-flash

    honest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.56
    ActionCreators
    -0.55
     Normdatei
    -0.54
    RegressionTest
    -0.50
    Geographie
    -0.49
    Rama
    -0.48
    titleMargin
    -0.47
     CCPA
    -0.47
    Попис
    -0.46
    InitVars
    -0.45
    POSITIVE LOGITS
     honest
    0.54
    honest
    0.49
     sincero
    0.48
    honestly
    0.48
    Honest
    0.47
     Honest
    0.45
     honestly
    0.44
     Honestly
    0.43
    genu
    0.42
    Honestly
    0.42
    Activations Density 0.137%

    No Known Activations