© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6639
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and processes in synchronization and failure between devices

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

    scientific or technical terms related to research, particularly focusing on factors, materials, variables, and information within academic contexts.

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

    words that represent important explanatory variables or causal factors in technical and scientific contexts.

    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
     recupero
    -0.38
     käyt
    -0.36
     diterapkan
    -0.36
     caminhada
    -0.36
     appartiennent
    -0.36
     contratación
    -0.36
     giudi
    -0.35
    Manufactured
    -0.35
     aprendiz
    -0.35
    Trung
    -0.35
    POSITIVE LOGITS
     providing
    1.07
     producing
    1.03
     giving
    1.02
     requiring
    0.98
     delivering
    0.97
     exhibiting
    0.95
     offering
    0.94
     showing
    0.94
     presenting
    0.93
     allowing
    0.92
    Activations Density 1.470%

    No Known Activations