© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 84371
    Prev
    Next
    INDEX
    Explanations

    elements and formatting indicative of structured or list-like content in technical documents

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

    creation, formation, completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ⓘ
    -0.28
    кну
    -0.25
    –¿
    -0.25
    talking
    -0.24
    Talking
    -0.22
    ẩn
    -0.22
     innovate
    -0.22
     مُعرِّف
    -0.22
     обрабаты
    -0.22
    __":
    -0.21
    POSITIVE LOGITS
     creation
    1.34
     introduction
    1.13
     formation
    1.13
     imposition
    1.12
     establishment
    1.11
     removal
    1.09
     issuance
    1.05
     provision
    1.05
     adoption
    1.05
     completion
    1.03
    Activations Density 0.270%

    No Known Activations