© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63218
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive forms related to individuals and communities

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

    subjects/objects after certain pronouns/articles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     and
    -0.43
    ,
    -0.39
    1
    -0.36
    ;
    -0.35
    2
    -0.35
     both
    -0.34
    3
    -0.31
    -
    -0.30
     either
    -0.30
    y
    -0.30
    POSITIVE LOGITS
     ſind
    1.02
     Verſ
    1.02
     verſ
    0.95
     myſelf
    0.94
     queſta
    0.91
    majánló
    0.90
    ſſung
    0.90
     ſta
    0.90
    <unused3>
    0.88
    <unused68>
    0.88
    Activations Density 0.141%

    No Known Activations