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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10216
    Prev
    Next
    INDEX
    Explanations

    references to Danish pop culture and entertainers

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

    in Norwegian or Swedish

    np_acts-logits-general · gemini-2.0-flash

    Norwegian and Swedish words

    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
    ampingi
    -0.39
     forskj
    -0.37
     natin
    -0.34
    læg
    -0.32
    følge
    -0.30
     équi
    -0.30
     húmedo
    -0.29
     fortsatt
    -0.29
     patrocin
    -0.28
     fær
    -0.28
    POSITIVE LOGITS
     محفوظة
    0.89
    niſſe
    0.83
    ſelben
    0.82
     FetchType
    0.80
    DockStyle
    0.78
    __.__
    0.77
    iſchen
    0.77
     ModelExpression
    0.76
    AnchorStyles
    0.76
    ValueStyle
    0.75
    Activations Density 0.086%

    No Known Activations