© 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. 10-GEMMASCOPE-RES-16K
    11. 15025
    Prev
    Next
    INDEX
    Explanations

    text that initiates a new section or paragraph in a document, often represented by specific token markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.53
    getContentPane
    -0.50
    不可能
    -0.50
    fun
    -0.48
    нца
    -0.48
    __":
    -0.46
    ,
    -0.46
     FOC
    -0.45
    ;
    -0.45
    काल
    -0.45
    POSITIVE LOGITS
     rowspan
    4.10
    multirow
    1.30
     colspan
    1.20
     InputDecoration
    1.14
    enumi
    1.05
    enumii
    1.03
     referrerpolicy
    1.00
     jspb
    0.87
    CompilerServices
    0.85
    tagHelperRunner
    0.82
    Activations Density 0.003%

    No Known Activations