© 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. 8546
    Prev
    Next
    INDEX
    Explanations

    phrases and requests related to taking action, particularly in terms of engagement or interaction

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

    followed by punctuation/conjunction

    np_acts-logits-general · gemini-2.0-flash

    calls to 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
     المعيارى
    -0.79
     waardoor
    -0.70
     оригіналу
    -0.64
     wherefore
    -0.63
     nên
    -0.63
    ніципа
    -0.62
    RectangleBorder
    -0.61
     raiſ
    -0.61
    WithIOException
    -0.61
     owing
    -0.60
    POSITIVE LOGITS
    吧
    1.05
     yourself
    1.01
     吧
    0.90
     dulu
    0.84
     NOW
    0.83
     nhé
    0.83
     ASAP
    0.82
     please
    0.82
     eens
    0.76
     yourselves
    0.76
    Activations Density 0.339%

    No Known Activations