© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9675
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.29
    NUMX
    -1.25
    ſelf
    -1.18
    ſelves
    -1.17
     themſelves
    -1.11
     Efq
    -1.09
     pleaſure
    -1.08
     faſt
    -1.07
     myſelf
    -1.07
     leaſt
    -1.05
    POSITIVE LOGITS
    .(
    0.67
    .
    0.67
    ."
    0.64
    ?
    0.63
    ↵
    0.59
     =
    0.58
     .
    0.58
    <eos>
    0.57
     (
    0.55
     [
    0.54
    Activations Density 0.437%

    No Known Activations