© 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. 13668
    Prev
    Next
    INDEX
    Explanations

    code-related structures and keywords, particularly in programming languages

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

    Code referencing sets, items, or files

    np_acts-logits-general · gemini-2.0-flash

    first occurrences of words

    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
     فريبيس
    -0.71
     terakhir
    -0.67
     последних
    -0.66
    glEnd
    -0.65
     second
    -0.65
     الأخيرة
    -0.64
     آخر
    -0.64
     secondary
    -0.63
     послед
    -0.63
    setVerticalGroup
    -0.62
    POSITIVE LOGITS
     first
    0.93
    first
    0.85
     pertama
    0.83
    First
    0.81
     First
    0.77
     primera
    0.75
     eerste
    0.72
     erster
    0.71
     primero
    0.71
     primeira
    0.71
    Activations Density 0.986%

    No Known Activations