© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2901
    Prev
    Next
    INDEX
    Explanations

    elements related to string concatenation and formatting in code

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

    code or programming-related syntax elements, particularly string concatenation and spacing in code.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     colgantes
    -0.37
     divisão
    -0.35
     migrator
    -0.34
     conductores
    -0.33
    leiter
    -0.32
     kemenangan
    -0.32
    chufe
    -0.30
     operações
    -0.30
     artesanía
    -0.30
     rueda
    -0.30
    POSITIVE LOGITS
    nbsp
    0.73
      
    0.66
    space
    0.66
     يتيمه
    0.66
     SPACE
    0.65
    Space
    0.64
     ModelExpression
    0.63
    WriteTagHelper
    0.62
    SPACE
    0.62
    ␣
    0.62
    Activations Density 0.287%

    No Known Activations