© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 84377
    Prev
    Next
    INDEX
    Explanations

    references to pronouns and their associated gendered forms

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

    pronouns followed by actions or descriptions

    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
     autorytatywna
    -0.65
     GenerationType
    -0.65
    Diweddarwch
    -0.62
    parsedMessage
    -0.59
     ProtoMessage
    -0.55
     AssemblyTitle
    -0.52
     مرئيه
    -0.50
    ⓧ
    -0.49
    UnusedPrivate
    -0.49
     initComponents
    -0.49
    POSITIVE LOGITS
     valueForKey
    0.37
    Baseball
    0.36
    Root
    0.35
    pecto
    0.35
     Baseball
    0.35
    hoben
    0.35
    Miscellaneous
    0.35
     Oil
    0.34
    Row
    0.34
     остро
    0.34
    Activations Density 0.396%

    No Known Activations