Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24185
    Prev
    Next
    INDEX
    Explanations

    references to male pronouns, especially "he."

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

    He followed by action

    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
    出版年
    -0.56
     Bourgoin
    -0.54
    SequentialGroup
    -0.48
     artificiales
    -0.47
     kasarigan
    -0.46
     uș
    -0.46
     trasparente
    -0.45
    rvore
    -0.44
    osidad
    -0.43
     intenção
    -0.43
    POSITIVE LOGITS
    He
    0.63
     disambiguazione
    0.59
    They
    0.56
     autorytatywna
    0.53
    Them
    0.52
    <bos>
    0.51
    にほんブログ村
    0.50
    uxxxx
    0.50
    RegressionTest
    0.50
    webElementXpaths
    0.50
    Activations Density 0.015%

    No Known Activations