© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13623
    Prev
    Next
    INDEX
    Explanations

    requests for donations and assistance

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

    Requests or questions including "please", "tell", or "can you"

    np_acts-logits-general · gemini-2.0-flash

    please and requests

    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
    niosek
    -0.60
    vington
    -0.56
    FlatAppearance
    -0.55
    GEBURTS
    -0.54
    难怪
    -0.54
     choix
    -0.52
     néz
    -0.51
     getSource
    -0.51
     Мексичка
    -0.51
    こいつ
    -0.50
    POSITIVE LOGITS
     please
    2.88
    please
    2.52
     Please
    2.50
    Please
    2.42
     PLEASE
    2.31
    PLEASE
    2.07
     pls
    2.05
     plz
    2.00
     bitte
    1.74
     Pls
    1.67
    Activations Density 0.262%

    No Known Activations