© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    terms related to data science and machine learning applications

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

    technical and specialized terminology from various domains like computer science, biology, and medicine.

    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
     dieß
    -0.40
     hefyd
    -0.34
     vroeg
    -0.34
    reactivex
    -0.33
     Jangan
    -0.33
    engk
    -0.33
    NEVER
    -0.33
    🗡
    -0.33
     Misalnya
    -0.32
     μὲν
    -0.32
    POSITIVE LOGITS
     efforts
    0.63
     ſche
    0.63
    CloseOperation
    0.61
     scheme
    0.57
     program
    0.56
     scenario
    0.56
    tagHelperRunner
    0.54
     project
    0.54
    ductory
    0.54
    ſelves
    0.54
    Activations Density 1.017%

    No Known Activations