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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15059
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their connections within Fijian history

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

    Fijian, Pacific, and Samoan contexts

    np_acts-logits-general · gemini-2.0-flash

    Pacific islands and peoples

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     transfieras
    -0.54
     صوتيه
    -0.52
    chyma
    -0.44
    tagHelperRunner
    -0.44
    ArgsConstructor
    -0.43
    OGND
    -0.42
    ValueStyle
    -0.42
    SuspendLayout
    -0.41
    +#+#
    -0.41
    MessageTagHelper
    -0.41
    POSITIVE LOGITS
     Fiji
    0.77
    Fiji
    0.70
     Samoa
    0.64
    
    0.58
     Fij
    0.56
     PNG
    0.51
     Papua
    0.51
     Pacific
    0.51
    Samoa
    0.50
     Guam
    0.48
    Activations Density 0.049%

    No Known Activations