© 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. 18-GEMMASCOPE-RES-16K
    11. 2859
    Prev
    Next
    INDEX
    Explanations

    numerical representations and data formats

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

    Numbers within lines of text

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -1.05
    исленность
    -1.03
    Rhestr
    -0.97
    Portale
    -0.96
     EconPapers
    -0.92
     SafeMath
    -0.90
    ItemBackground
    -0.87
    
    -0.86
    تقاوى
    -0.83
    QMetaType
    -0.82
    POSITIVE LOGITS
    3
    0.72
    4
    0.68
    5
    0.67
    1
    0.65
    2
    0.65
    7
    0.61
     
    0.61
    9
    0.60
    6
    0.60
    8
    0.55
    Activations Density 2.553%

    No Known Activations