Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4111
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and methods that handle data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.59
     opri
    -0.55
    OHN
    -0.49
    itored
    -0.48
    ólica
    -0.48
    ybė
    -0.47
     somos
    -0.46
    >';
    
    -0.46
     ';
    
    -0.45
    getProject
    -0.45
    POSITIVE LOGITS
    ReadLine
    1.24
    SourceChecksum
    1.04
    readLine
    1.02
    nextLine
    0.99
    NewGuid
    0.96
     '\\;'
    0.87
    randomUUID
    0.81
    ReadKey
    0.76
    EDEFAULT
    0.74
    drawSprites
    0.74
    Activations Density 0.083%

    No Known Activations