© 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. 35-GEMMASCOPE-RES-16K
    11. 14114
    Prev
    Next
    INDEX
    Explanations

    features of portable electronic devices, particularly related to their usability and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geslacht
    -0.35
    jspx
    -0.35
     الأم
    -0.34
    geslacht
    -0.30
    Biografie
    -0.30
    ismet
    -0.30
    getCustomer
    -0.30
    memcmp
    -0.29
     vierge
    -0.28
    lamabad
    -0.28
    POSITIVE LOGITS
     portable
    1.83
     portability
    1.78
     compact
    1.55
    portable
    1.53
     Portable
    1.52
    Portable
    1.49
     compactness
    1.38
     portátil
    1.33
     kompakt
    1.32
     компакт
    1.31
    Activations Density 0.449%

    No Known Activations