© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8699
    Prev
    Next
    INDEX
    Explanations

    specific code structures or patterns in programming languages, possibly related to error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.82
    
    -0.78
    WriteTagHelper
    -0.78
    bootstrapcdn
    -0.76
     محفوظة
    -0.75
    AutoScale
    -0.69
    rungsseite
    -0.68
    WebVitals
    -0.68
     <<<<<<<<<<<<<<
    -0.66
    httphttps
    -0.66
    POSITIVE LOGITS
     transfieras
    0.47
    ̈́
    0.45
    ώς
    0.44
     vendar
    0.44
    camente
    0.43
    terday
    0.43
    LikeLike
    0.42
     cream
    0.41
    icitis
    0.41
    osamente
    0.41
    Activations Density 0.236%

    No Known Activations