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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3288
    Prev
    Next
    INDEX
    Explanations

    references to political events and governmental structures

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

    Iran or Iranian people

    np_acts-logits-general · gemini-2.0-flash

    Iranian places and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    XmlEnum
    -0.76
     Normdatei
    -0.58
    TabStop
    -0.54
     Otter
    -0.54
     وتسجيلات
    -0.53
     CreateTagHelper
    -0.52
     transférez
    -0.52
     crossorigin
    -0.52
    )\}$
    -0.51
     Cajun
    -0.51
    POSITIVE LOGITS
     Iran
    1.19
     Iranian
    1.17
     Tehran
    1.13
    Iran
    1.07
    Iranian
    0.99
     iran
    0.93
     Irán
    0.90
     Persian
    0.85
     IR
    0.84
    Teh
    0.76
    Activations Density 0.172%

    No Known Activations