© 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. 16-GEMMASCOPE-RES-16K
    11. 5293
    Prev
    Next
    INDEX
    Explanations

    mentions of various people in the text

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

    Pronouns followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    reporting what someone told him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.74
     writ
    -0.51
     通販
    -0.51
    Bronnen
    -0.50
     Exacts
    -0.50
    orama
    -0.46
    rhein
    -0.46
    antMatchers
    -0.45
    存于互联网档案馆
    -0.44
    rachtet
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.80
     what
    0.74
     how
    0.72
     everything
    0.69
    EndProject
    0.67
     anything
    0.66
     mouthful
    0.63
    
    0.61
     about
    0.59
     vänner
    0.59
    Activations Density 0.108%

    No Known Activations