© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    phrases and references that relate to personal experiences, perspectives, or testimonies

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

    Precedes "whole" or "entire"

    np_acts-logits-general · gemini-2.0-flash

    whole and entire

    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
    SharedCtor
    -0.64
     فريبيس
    -0.61
     للاسماء
    -0.60
     Italijani
    -0.59
    tvguidetime
    -0.57
    Brainz
    -0.56
     onAnimation
    -0.56
    msgTypes
    -0.55
     nakalista
    -0.54
    +:+
    -0.54
    POSITIVE LOGITS
     whole
    3.93
     entire
    3.85
    whole
    3.63
    entire
    3.16
    Whole
    3.14
     Entire
    3.13
     WHOLE
    2.97
     Whole
    2.87
     ENTIRE
    2.82
    Entire
    2.82
    Activations Density 0.661%

    No Known Activations