© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4652
    Prev
    Next
    INDEX
    Explanations

    instances of brackets and punctuation related to citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cause
    -0.35
     Cause
    -0.34
    cause
    -0.31
    ByVersion
    -0.31
     forget
    -0.31
     odkazy
    -0.30
     row
    -0.30
     hal
    -0.29
    oubliez
    -0.29
    AnchorTagHelper
    -0.29
    POSITIVE LOGITS
    httphttps
    0.79
     ProtoMessage
    0.74
     <>",
    0.71
    GIVEREF
    0.69
     समीक्षक
    0.68
     ujednoznacz
    0.68
    tagHelperRunner
    0.67
     Chwiliwch
    0.63
    WriteTagHelper
    0.62
    sizeCache
    0.61
    Activations Density 0.258%

    No Known Activations