© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 7065
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or words that emphasize continuance or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.91
     ſaid
    -0.71
     houſe
    -0.70
     purpoſe
    -0.69
     larmes
    -0.68
     pleaſure
    -0.68
     ſmall
    -0.67
     Inscrivez
    -0.67
     Connectez
    -0.66
     fevere
    -0.65
    POSITIVE LOGITS
    ChildScrollView
    1.12
    parsedMessage
    1.01
     estekak
    0.91
    oa̍t
    0.85
    StreetMap
    0.85
    Portail
    0.83
    bewerken
    0.82
    yntaxException
    0.81
    かわらず
    0.81
    ViewFeatures
    0.80
    Activations Density 0.574%

    No Known Activations