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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 122392
    Prev
    Next
    INDEX
    Explanations

    mentions of Samoan identity and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AndroidJUnit
    -0.51
    ArgsConstructor
    -0.51
    __":
    
    -0.51
     cref
    -0.51
    InjectAttribute
    -0.50
     Arkham
    -0.50
    TintMode
    -0.50
     ModelExpression
    -0.49
    ChildScrollView
    -0.49
     PropTypes
    -0.48
    POSITIVE LOGITS
     Samoa
    0.90
    ronesia
    0.87
    
    0.77
     Polynesian
    0.76
     Polynesia
    0.76
    Samoa
    0.71
     Fiji
    0.69
     Hawaiian
    0.64
     islands
    0.63
    Fiji
    0.63
    Activations Density 0.020%

    No Known Activations