© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63492
    Prev
    Next
    INDEX
    Explanations

    specific performance metrics and efficiency indicators in processes or algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.42
     postup
    -0.34
     Sociales
    -0.31
     importance
    -0.29
    openzeppelin
    -0.29
    ichthys
    -0.29
     letti
    -0.29
    PostConstruct
    -0.28
    addGap
    -0.28
     risk
    -0.28
    POSITIVE LOGITS
    Efficiency
    0.76
     Efficiency
    0.75
     efficiency
    0.75
    efficiency
    0.74
    speed
    0.72
    Хьажоргаш
    0.69
    Speed
    0.69
     speed
    0.66
    efficient
    0.66
    SPEED
    0.65
    Activations Density 0.159%

    No Known Activations