© 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. 60678
    Prev
    Next
    INDEX
    Explanations

    references to male and female pronouns, indicating discussions about specific individuals

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

    pronoun followed by verb

    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
    featureID
    -0.72
    ロウィン
    -0.65
    IntoConstraints
    -0.60
     müſſen
    -0.58
     <=",
    -0.57
     メンテナ
    -0.56
     ddelwed
    -0.56
     Weiſe
    -0.56
    <unused14>
    -0.56
    <unused41>
    -0.56
    POSITIVE LOGITS
    UnusedPrivate
    0.43
    enderror
    0.40
    Tembelea
    0.35
    tamment
    0.32
    AddTagHelper
    0.32
    flashdata
    0.32
     Nachfolger
    0.32
     tartalomajánló
    0.32
     nakalista
    0.30
    Predecesor
    0.28
    Activations Density 0.009%

    No Known Activations