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. 20-GEMMASCOPE-RES-131K
    6. 5298
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate complexity, challenges, and significant changes in a narrative or context

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

    specific condition or characteristic

    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
    OGND
    -0.77
     typelib
    -0.71
     للمعارف
    -0.71
     noDo
    -0.70
    #+#
    -0.68
     Paglinawan
    -0.68
     Italijanski
    -0.68
    GraphicsUnit
    -0.68
     queſta
    -0.68
     zwiſchen
    -0.67
    POSITIVE LOGITS
    :
    0.63
    ,
    0.57
    ;
    0.56
    .
    0.46
     
    0.44
     -
    0.41
     At
    0.40
     –
    0.39
     gere
    0.38
     because
    0.38
    Activations Density 0.138%

    No Known Activations