© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6913
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sneaky or stealthy actions

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

    Follows prefixes "re-", "s(n)e-", "twe-", "ple-", "le-", "bele-", "scre-"

    np_acts-logits-general · gemini-2.0-flash

    replead, plead, believe, sneaked, gleefully, tweeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.53
    ئو
    -0.46
    NgModule
    -0.45
     članak
    -0.45
     obstante
    -0.45
    iles
    -0.45
    INARY
    -0.44
     serca
    -0.43
    les
    -0.43
    DEF
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    ath
    0.66
    eting
    0.60
    eping
    0.59
     jScrollPane
    0.58
    fromnode
    0.55
    ats
    0.55
    aling
    0.55
    MergeFrom
    0.55
    alth
    0.55
    Activations Density 0.228%

    No Known Activations