© 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. 2-GEMMASCOPE-RES-16K
    11. 8577
    Prev
    Next
    INDEX
    Explanations

    references to specific academic or scholarly works and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.71
    RefNanny
    -0.60
    Наводи
    -0.59
    majánló
    -0.59
    ########.
    -0.59
    InjectAttribute
    -0.59
     propOrder
    -0.59
    AndEndTag
    -0.57
     esternos
    -0.57
    enderror
    -0.57
    POSITIVE LOGITS
     gut
    0.71
    ner
    0.68
     Gut
    0.55
    NER
    0.55
     butter
    0.53
    gut
    0.52
    Gut
    0.50
     guts
    0.50
     nerves
    0.49
    nerv
    0.49
    Activations Density 0.553%

    No Known Activations