© 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. 9-GEMMASCOPE-RES-131K
    11. 29512
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns or indications of possession

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

    's or t

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

    The neuron detects tokens that contain an apostrophe marking contractions or clitic suffixes.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    This neuron detects tokens that are apostrophe-containing contractions or clitic forms (e.g., n't, 'm, 're, 've).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steder
    -0.41
     colgante
    -0.38
     indépendante
    -0.37
     corrupción
    -0.34
     nación
    -0.34
     mecánica
    -0.33
     fachada
    -0.33
     contenedores
    -0.32
     précédentes
    -0.32
     solución
    -0.31
    POSITIVE LOGITS
     kaarangay
    0.88
    <unused16>
    0.81
    <pad>
    0.81
    [@BOS@]
    0.81
    <unused43>
    0.81
    <unused28>
    0.81
    <unused52>
    0.81
    <unused74>
    0.81
    <unused8>
    0.81
    <unused23>
    0.81
    Activations Density 0.040%

    No Known Activations