© 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. 12468
    Prev
    Next
    INDEX
    Explanations

    terminology related to research methodologies and analytical tools

    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
    المناصب
    -0.51
    webElementXpaths
    -0.48
     protoimpl
    -0.40
    rawDesc
    -0.38
     تانيه
    -0.37
    hoeddwyd
    -0.37
     Tate
    -0.37
    onedDateTime
    -0.36
    sendRedirect
    -0.35
     Sach
    -0.35
    POSITIVE LOGITS
     tools
    3.33
     tool
    3.31
     Tools
    2.94
     Tool
    2.86
    工具
    2.81
    tool
    2.81
     outils
    2.73
    tools
    2.70
     herramientas
    2.67
    Tool
    2.64
    Activations Density 0.608%

    No Known Activations