© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2606
    Prev
    Next
    INDEX
    Explanations

    terms related to guidance, support, and collaboration in leadership contexts

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

    Need of direction, help, or opportunity

    np_acts-logits-general · gemini-2.0-flash

    giving direction or help

    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
    WriteTagHelper
    -0.66
    DataContract
    -0.53
     Bourgoin
    -0.53
    MergeFrom
    -0.52
    HttpPut
    -0.51
    almaz
    -0.50
    EObject
    -0.49
    AndEndTag
    -0.49
    ciclopedia
    -0.49
    ándolos
    -0.49
    POSITIVE LOGITS
     clarity
    0.93
     flexibility
    0.87
     insight
    0.82
     tangible
    0.80
     excitement
    0.80
     transparency
    0.80
     opportunities
    0.79
     stability
    0.78
     exposure
    0.78
     ways
    0.77
    Activations Density 0.359%

    No Known Activations