© 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. 25-GEMMASCOPE-RES-16K
    11. 7482
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to personal growth and the challenges that accompany stepping out of one's comfort zone

    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
    UnusedPrivate
    -0.89
    setVerticalGroup
    -0.73
    vician
    -0.71
    NewUrlParser
    -0.71
    ///</
    -0.66
     Paglinawan
    -0.65
    DebuggerNonUser
    -0.63
    WriteTagHelper
    -0.62
    IndentedString
    -0.61
    навли
    -0.61
    POSITIVE LOGITS
     squarely
    0.70
     firmly
    0.66
     smack
    0.63
     headlong
    0.61
     seamlessly
    0.60
     solidly
    0.58
     decisively
    0.57
     definitively
    0.56
     resolutely
    0.55
     unwittingly
    0.55
    Activations Density 0.447%

    No Known Activations