© 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. 12690
    Prev
    Next
    INDEX
    Explanations

    semicolon and closing parenthesis symbols commonly used in programming syntax

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

    Code snippets (often incomplete) ending with delimiters

    np_acts-logits-general · gemini-2.0-flash

    code statement endings

    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
     betweenstory
    -0.65
    Spoljašnje
    -0.62
    esez
    -0.62
     plein
    -0.60
     nahilalakip
    -0.60
    Fcn
    -0.58
     MCQ
    -0.57
     hassle
    -0.56
    anej
    -0.56
     lele
    -0.56
    POSITIVE LOGITS
    AddTagHelper
    0.67
    endpush
    0.64
    二是
    0.63
    æus
    0.61
    ientôt
    0.54
    יוחד
    0.54
     tajam
    0.51
    المشاركات
    0.51
    utsches
    0.51
    はじめに
    0.51
    Activations Density 0.099%

    No Known Activations