© 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. 24-GEMMASCOPE-RES-16K
    11. 3069
    Prev
    Next
    INDEX
    Explanations

    references to political figures and corruption allegations

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

    Brazilian political figures/acronyms

    np_acts-logits-general · gemini-2.0-flash

    Brazil political and financial news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAttribute
    -0.58
     auténtica
    -0.58
     MainAxisSize
    -0.58
     traseira
    -0.56
    PreferredItem
    -0.56
     semelh
    -0.54
    kään
    -0.54
     pistolet
    -0.53
    providedIn
    -0.52
     almofada
    -0.52
    POSITIVE LOGITS
    expandindo
    0.70
    Referências
    0.50
    typeorm
    0.36
     fund
    0.36
     artig
    0.36
     érté
    0.35
     remo
    0.34
     anal
    0.33
    ㅤㅤ
    0.33
     process
    0.33
    Activations Density 0.513%

    No Known Activations