© 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 EvalsExportsAPI 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. 35000
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns, indicating a focus on personal experiences or identity

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

    for me or us

    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
    QUENCE
    -0.64
     виправивши
    -0.55
     plegable
    -0.51
     дописавши
    -0.51
     abstrato
    -0.50
    acité
    -0.50
    edicated
    -0.49
     Witte
    -0.48
     pensieri
    -0.48
     navideño
    -0.47
    POSITIVE LOGITS
     endfor
    0.60
     forKey
    0.57
    ForType
    0.55
    ForKey
    0.49
    for
    0.47
    tagHelperRunner
    0.47
    forKey
    0.47
    ؤلاء
    0.46
    ForValue
    0.46
     fürs
    0.45
    Activations Density 0.014%

    No Known Activations