© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11504
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and evaluations of size and value in contexts like prices and dimensions

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

    Followed by "for"

    np_acts-logits-general · gemini-2.0-flash

    preposition "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.04
    endphp
    -0.98
    脚注の使い方
    -0.95
    DockStyle
    -0.95
     صوتيه
    -0.94
     Normdatei
    -0.88
    ArgsConstructor
    -0.86
    jspx
    -0.83
    TintMode
    -0.82
    期刊论文
    -0.82
    POSITIVE LOGITS
     for
    1.88
     bagi
    1.63
     עבור
    1.25
     für
    1.20
     для
    1.19
    for
    1.16
     dla
    1.16
     بالنسبة
    1.08
     voor
    1.04
    สำหรับ
    0.91
    Activations Density 0.702%

    No Known Activations