© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and experiences

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

    First-person pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    I feel/was/am experiencing

    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
    心想
    -0.62
     uważ
    -0.62
     Hoping
    -0.61
     claiming
    -0.61
     admits
    -0.59
     думал
    -0.59
     thinking
    -0.58
     hoping
    -0.58
    Hoping
    -0.57
     insists
    -0.57
    POSITIVE LOGITS
    évaluateur
    0.74
     EnglishChoose
    0.72
     missed
    0.70
     виправивши
    0.64
     acert
    0.60
     giustizia
    0.60
    enterOuterAlt
    0.58
     dodged
    0.58
     snippetHide
    0.57
     owe
    0.57
    Activations Density 0.188%

    No Known Activations