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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 35581
    Prev
    Next
    INDEX
    Explanations

    references to research methodology and the study's context within a specific cultural or regional framework

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

    Iranian cities and population

    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
     Perlu
    -0.32
     став
    -0.30
     Caribbean
    -0.29
     tró
    -0.28
    eapples
    -0.27
    Nuorodos
    -0.27
    Източници
    -0.26
     ouver
    -0.26
     nevera
    -0.26
     tişört
    -0.26
    POSITIVE LOGITS
     Tehran
    0.75
     Iranian
    0.72
    Iran
    0.72
     Iran
    0.71
     persian
    0.69
     iran
    0.67
    Iranian
    0.65
    fahan
    0.65
    endpush
    0.65
     Persian
    0.62
    Activations Density 0.069%

    No Known Activations