© 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. 20-GEMMASCOPE-RES-16K
    11. 15284
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and reactions

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

    First-person statements expressing feelings

    np_acts-logits-general · gemini-2.0-flash

    states of being or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ftate
    -0.65
     fubject
    -0.58
     Chriftian
    -0.57
    צלחה
    -0.56
     neceff
    -0.55
    ктан
    -0.55
     Relo
    -0.53
    ſelf
    -0.53
     Pliocene
    -0.52
    saraba
    -0.52
    POSITIVE LOGITS
     intrigued
    0.78
     impressed
    0.78
     amazed
    0.66
     convinced
    0.63
     skeptical
    0.62
     curious
    0.60
     thrilled
    0.59
     impress
    0.58
     perplexed
    0.58
     puzzled
    0.57
    Activations Density 0.214%

    No Known Activations