© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 361
    Prev
    Next
    INDEX
    Explanations

    concepts related to educational methodologies and technology

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

    discussions about implementing educational technology and innovative teaching methods to enhance student learning outcomes.

    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
     estekak
    -0.55
    ScopeManager
    -0.54
     ब्रेकडाउन
    -0.52
     AssemblyCompany
    -0.50
     &___
    -0.47
    INERY
    -0.44
    iseries
    -0.44
    衛隊
    -0.43
     lucu
    -0.42
     Sodom
    -0.42
    POSITIVE LOGITS
     learning
    1.00
     Learning
    0.83
     learners
    0.81
     aprendizagem
    0.81
    Learning
    0.79
     learner
    0.79
    learning
    0.76
     Learners
    0.73
     LEARNING
    0.72
    Learner
    0.72
    Activations Density 0.270%

    No Known Activations