© 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. 9-GEMMASCOPE-RES-131K
    11. 18109
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referring to the first and second person

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

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Theſe
    -0.66
     ujednoznacz
    -0.66
     avoient
    -0.60
     increí
    -0.57
     itſelf
    -0.56
    ⟬
    -0.56
     Beſ
    -0.55
     myſelf
    -0.54
     kolye
    -0.54
     ſal
    -0.54
    POSITIVE LOGITS
     in
    0.86
     In
    0.67
     dans
    0.66
     nella
    0.62
     dalam
    0.61
     trong
    0.60
     в
    0.60
     Nella
    0.60
    InThe
    0.58
     within
    0.57
    Activations Density 0.053%

    No Known Activations