© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37354
    Prev
    Next
    INDEX
    Explanations

    technical specifications and architectural details related to computing systems

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

    system architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     conven
    -0.33
     shout
    -0.31
    ברס
    -0.31
    MethodManager
    -0.30
     Wikisource
    -0.30
     Conven
    -0.30
    usercontent
    -0.29
     Git
    -0.29
     pay
    -0.29
     fork
    -0.29
    POSITIVE LOGITS
     architecture
    1.32
     architectures
    1.20
     arquitetura
    1.19
     arquitectura
    1.18
    architecture
    1.16
     Architecture
    1.12
    Architecture
    1.10
     ARCHITECTURE
    1.07
     architectural
    1.04
     arquitect
    1.02
    Activations Density 0.121%

    No Known Activations