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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1077
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

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

    staying in or on a place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.57
    MigrationBuilder
    -0.55
    CppMethod
    -0.55
    뀜
    -0.55
    Personensuche
    -0.53
    urlencoded
    -0.52
    PyExc
    -0.51
     cref
    -0.50
     שוליים
    -0.49
     تعدى
    -0.48
    POSITIVE LOGITS
    Stay
    0.69
     Stay
    0.69
     stay
    0.67
    stay
    0.62
    Stayed
    0.59
     STAY
    0.59
    STAY
    0.55
     stayed
    0.54
    Remain
    0.51
    Staying
    0.51
    Activations Density 0.021%

    No Known Activations