© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 76227
    Prev
    Next
    INDEX
    Explanations

    references to the second-person pronouns "you" and "your"

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

    you and your

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects direct second-person address—places where the text speaks to or questions the reader (explicitly addressing "you").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Diweddarwch
    -0.66
    </tfoot>
    -0.56
     OMITBAD
    -0.53
     kasarigan
    -0.53
     MERCHANTABILITY
    -0.52
    ⏜
    -0.51
    ondissement
    -0.51
     synergy
    -0.51
     franquicia
    -0.51
    ειτουργ
    -0.50
    POSITIVE LOGITS
     transférez
    0.41
     informée
    0.36
    WithIOException
    0.33
     Neutr
    0.31
     débat
    0.31
     lenker
    0.30
    contro
    0.29
     Acuerdo
    0.28
    apnews
    0.28
    DebuggerNonUser
    0.28
    Activations Density 0.000%

    No Known Activations