© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81816
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to places and events

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

    Angola, Timor, Mozambique, Cape Verde

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     aquarela
    -0.59
    bricas
    -0.52
     increí
    -0.52
     Económica
    -0.50
    invokeLater
    -0.50
     cerâmica
    -0.50
     térmica
    -0.49
     cardíaca
    -0.49
    /*
    -0.49
    mybatisplus
    -0.48
    POSITIVE LOGITS
     Angola
    0.51
    Angola
    0.46
    delwed
    0.40
    Rpc
    0.36
    êques
    0.35
    Aktualisiert
    0.35
     lê
    0.34
    phosa
    0.33
     aspir
    0.32
    TemporalType
    0.32
    Activations Density 0.018%

    No Known Activations