© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    affirmative responses or expressions of agreement

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

    Follows "yes" or "Yes"

    np_acts-logits-general · gemini-2.0-flash

    affirmative responses

    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
     ویکی‌پدیا
    -0.81
    +#+
    -0.77
    MLLoader
    -0.76
    يكب
    -0.70
     Roskov
    -0.68
    RTEE
    -0.68
    WireFormatLite
    -0.68
    RenderAtEndOf
    -0.67
    逅
    -0.67
    Datuak
    -0.66
    POSITIVE LOGITS
     indeed
    0.97
    sir
    0.89
    ssss
    0.80
    Indeed
    0.80
     Indeed
    0.78
    indeed
    0.74
     sir
    0.73
    sssss
    0.73
    sss
    0.72
    ssssssss
    0.71
    Activations Density 0.052%

    No Known Activations