© 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. 13255
    Prev
    Next
    INDEX
    Explanations

    technical terms and data related to research methodologies and results

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

    numerical data and statistical measurements presented in technical or 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
     afin
    -0.35
     wishing
    -0.30
     чтобы
    -0.30
    然后再
    -0.30
    并将
    -0.29
    jte
    -0.29
     zodat
    -0.29
     statt
    -0.28
    than
    -0.28
     щоб
    -0.28
    POSITIVE LOGITS
    AddTagHelper
    0.85
     queſta
    0.78
     tends
    0.78
    seemed
    0.78
     behaves
    0.78
     seems
    0.78
     ſche
    0.77
     suffers
    0.75
     seemed
    0.75
     contains
    0.75
    Activations Density 1.951%

    No Known Activations