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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7804
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and integrity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.68
    tagHelper
    -0.62
     noDo
    -0.61
    MockMvc
    -0.58
     Италијани
    -0.57
    istible
    -0.57
     Paglinawan
    -0.57
    EndTag
    -0.56
    vscode
    -0.55
     timedelta
    -0.55
    POSITIVE LOGITS
     honesty
    1.65
     honest
    1.50
     admitting
    1.39
     Honesty
    1.34
     admit
    1.33
     truth
    1.32
     candid
    1.32
    honest
    1.30
     frank
    1.29
     confess
    1.28
    Activations Density 0.483%

    No Known Activations