© 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. 8370
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or existing conditions

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

    Follows words like "so", "had", "is", "or"

    np_acts-logits-general · gemini-2.0-flash

    already / 已

    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
     CreateTagHelper
    -0.72
     كومونز
    -0.70
     ISNI
    -0.59
     싶
    -0.54
    DataAnnotations
    -0.53
    Демографія
    -0.52
     NUKAT
    -0.52
     وصلة
    -0.52
    MLLoader
    -0.51
    Einzelnachweise
    -0.50
    POSITIVE LOGITS
     already
    4.57
    already
    4.12
     Already
    3.94
    Already
    3.81
     ALREADY
    3.52
     allerede
    2.97
     уже
    2.86
    ALREADY
    2.85
     redan
    2.84
     déjà
    2.84
    Activations Density 0.832%

    No Known Activations