© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3090
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to mathematical expressions and references in academic texts

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

    Follows bracketed references (e.g., \[...])

    np_acts-logits-general · gemini-2.0-flash

    since, because, the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     externi
    -0.52
    UTOR
    -0.49
    scriptcase
    -0.49
    adpleegd
    -0.48
    บอก
    -0.45
    vitt
    -0.45
    UPAC
    -0.44
     BorderRadius
    -0.44
    audiovisuel
    -0.43
     spoons
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.71
    RegressionTest
    0.71
    الحياه
    0.71
    IsContent
    0.68
    ConstraintMaker
    0.65
    PerformLayout
    0.63
     endblock
    0.62
     mergeFrom
    0.61
     noDo
    0.57
     propOrder
    0.56
    Activations Density 1.519%

    No Known Activations