© 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. 22-GEMMASCOPE-RES-16K
    11. 7028
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intent

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

    "to" followed by an action

    np_acts-logits-general · gemini-2.0-flash

    used to express purpose or action

    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
     using
    -1.00
    using
    -0.90
    use
    -0.86
     use
    -0.82
    Using
    -0.81
     Using
    -0.79
    Use
    -0.78
     menggunakan
    -0.76
     Use
    -0.74
     uses
    -0.73
    POSITIVE LOGITS
     purposes
    0.70
     interchangeably
    0.68
     качестве
    0.66
     denote
    0.65
    χη
    0.64
     supplement
    0.62
     advantage
    0.62
    dym
    0.62
     describe
    0.60
     conjunction
    0.60
    Activations Density 0.338%

    No Known Activations