© 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. 73582
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or belonging

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

    indicating belonging to something

    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
    )')
    -0.52
    ⁃
    -0.49
    userDao
    -0.46
    Laser
    -0.44
    ')))
    -0.44
    SRS
    -0.43
     Normalmente
    -0.43
     FishBase
    -0.43
    maxWidth
    -0.43
    حتى
    -0.43
    POSITIVE LOGITS
     belong
    1.36
     Belong
    1.30
    belong
    1.26
     belonging
    1.23
     belongs
    1.22
     belonged
    1.20
    belongs
    1.11
     apparten
    0.92
     pertenecen
    0.82
     pertenece
    0.82
    Activations Density 0.011%

    No Known Activations