© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8671
    Prev
    Next
    INDEX
    Explanations

    references to political structures and leadership within specific contexts

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

    Names or titles, followed by a name

    np_acts-logits-general · gemini-2.0-flash

    president names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NUKAT
    -0.43
     Sitz
    -0.42
    Understood
    -0.40
    styp
    -0.40
    Становништво
    -0.38
    parency
    -0.37
    Recomendaciones
    -0.36
    ódnica
    -0.36
     معرف
    -0.35
     DLC
    -0.35
    POSITIVE LOGITS
    uterte
    0.83
    sonaro
    0.77
     Obrador
    0.76
    phosa
    0.73
     Mugabe
    0.68
     Erdogan
    0.67
     Uhuru
    0.66
     Erdoğan
    0.65
    riwal
    0.64
     Duterte
    0.63
    Activations Density 0.341%

    No Known Activations