© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8923
    Prev
    Next
    INDEX
    Explanations

    terms related to research funding and institutional support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    research and development (R&D) activities, institutions, and funding.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.66
     intptr
    -0.42
    
    -0.41
     iNdEx
    -0.41
     Wicidata
    -0.38
     mijne
    -0.38
    Personendaten
    -0.36
     vrijwilli
    -0.36
    ArgumentParser
    -0.35
    Herkunft
    -0.35
    POSITIVE LOGITS
     innovation
    1.10
    Innovation
    1.03
    innovation
    1.02
     Innovation
    0.98
     research
    0.97
     patent
    0.93
    Research
    0.92
     patents
    0.91
     innovación
    0.90
     Research
    0.88
    Activations Density 0.426%

    No Known Activations