© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2558
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and openness in communication

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

    Following "be" or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    truthfulness and candidness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.67
    :+:
    -0.63
     betweenstory
    -0.60
    tagHelper
    -0.56
     Paglinawan
    -0.54
    zné
    -0.53
    ":[{
    -0.52
    httphttps
    -0.52
    vscode
    -0.50
    
    -0.50
    POSITIVE LOGITS
     honest
    2.40
     honesty
    2.33
    honest
    2.11
     Honest
    2.02
    Honest
    1.94
     candid
    1.87
     frank
    1.87
     Honesty
    1.86
     truthful
    1.80
     honnête
    1.79
    Activations Density 0.296%

    No Known Activations