© 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. 22-GEMMASCOPE-RES-16K
    11. 15062
    Prev
    Next
    INDEX
    Explanations

    specific formats or structures in text, such as symbols, punctuation, and reference markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.40
     startX
    -0.35
     Sterling
    -0.34
     cervix
    -0.32
     fru
    -0.32
     Palae
    -0.31
     iLocal
    -0.31
     smoker
    -0.30
     Sun
    -0.30
     debt
    -0.29
    POSITIVE LOGITS
    Rhestr
    0.96
    Vidite
    0.64
     يتيمه
    0.62
    Ārējās
    0.60
    Aholisi
    0.59
    Erreferentziak
    0.59
     <>",
    0.59
    AutoModerator
    0.58
    FormTagHelper
    0.57
     للمعارف
    0.56
    Activations Density 1.435%

    No Known Activations