© 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. 24-GEMMASCOPE-RES-16K
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and code syntax

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

    "array" or "arrays"

    np_acts-logits-general · gemini-2.0-flash

    detecting arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.58
     &___
    -0.57
     Exacts
    -0.54
     Exactos
    -0.52
     Wolff
    -0.49
     Seat
    -0.49
    出版年
    -0.49
     uova
    -0.48
     Waters
    -0.48
    begre
    -0.47
    POSITIVE LOGITS
     array
    2.79
    array
    2.70
    Array
    1.94
     Array
    1.92
     arrays
    1.90
    ARRAY
    1.75
     ARRAY
    1.74
    数组
    1.50
    arrays
    1.46
     newArray
    1.43
    Activations Density 0.141%

    No Known Activations