© 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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10826
    Prev
    Next
    INDEX
    Explanations

    references to language and translation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.55
    
    -0.54
    DockStyle
    -0.49
     utafitiHapana
    -0.47
     CreateTagHelper
    -0.47
     ProtoMessage
    -0.46
     '\\;'
    -0.44
    localctx
    -0.43
    +#+#
    -0.42
    oredCriteria
    -0.42
    POSITIVE LOGITS
     English
    2.23
    English
    1.95
     english
    1.87
     ENGLISH
    1.75
    english
    1.58
    ENGLISH
    1.50
     Arabic
    1.49
    英語
    1.48
     Hindi
    1.46
     Spanish
    1.44
    Activations Density 0.722%

    No Known Activations