© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10311
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Brazil" and references to Brazil-related entities or persons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.50
    تقاوى
    -0.47
    adaptiveStyles
    -0.43
     medarbe
    -0.42
    ğraf
    -0.42
     relações
    -0.41
     gynhyrchwyd
    -0.41
     Mitarbeiter
    -0.40
     Mehr
    -0.40
    Weaknesses
    -0.39
    POSITIVE LOGITS
    drawable
    0.70
    Rio
    0.65
     Rio
    0.63
     spike
    0.58
    annotations
    0.54
     Brasil
    0.54
     Brazil
    0.54
     Brasilien
    0.54
     Gla
    0.53
     rio
    0.53
    Activations Density 0.428%

    No Known Activations