© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5845
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize honesty and transparency in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.54
    SBATCH
    -0.47
     disambiguazione
    -0.47
    scryfall
    -0.43
    thâu
    -0.41
     uLocal
    -0.41
    NameInMap
    -0.37
    ########.
    -0.37
     coorden
    -0.36
     Numerade
    -0.36
    POSITIVE LOGITS
     honest
    2.44
     honesty
    2.38
    honest
    2.09
     honestly
    1.95
    Honest
    1.93
     Honest
    1.91
     truthful
    1.88
     Honesty
    1.86
     honnête
    1.77
     frank
    1.70
    Activations Density 0.493%

    No Known Activations