© 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. 584
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery or tools

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

    tools and machinery, particularly saws, wrenches, and other hardware equipment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    dates and years (particularly four-digit years in the format 19XX or 20XX).

    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
     SwiftUI
    -0.52
     kasarigan
    -0.48
     Enix
    -0.48
     Nieren
    -0.48
    StoryboardSegue
    -0.45
    Formik
    -0.45
    momix
    -0.45
    fxml
    -0.43
     localObject
    -0.42
     CommonModule
    -0.42
    POSITIVE LOGITS
     tool
    0.90
    工具
    0.88
     tools
    0.85
     Tool
    0.82
    tool
    0.82
     Tools
    0.80
    Tool
    0.78
     herramienta
    0.76
     outils
    0.76
    tools
    0.75
    Activations Density 0.146%

    No Known Activations