© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28194
    Prev
    Next
    INDEX
    Explanations

    patterns related to error handling or response structure in programming

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

    demon, compared, vital bugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.51
    retudo
    -0.44
    cemic
    -0.43
     Angelo
    -0.43
    outer
    -0.41
     genomic
    -0.41
    dale
    -0.40
     innere
    -0.40
    Tikang
    -0.40
     natürlichen
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.79
     &___
    0.75
    tagHelperRunner
    0.75
    parsedMessage
    0.72
    stateProvider
    0.70
     resourceCulture
    0.68
     defaultstate
    0.65
    \}\\
    0.65
    InjectAttribute
    0.65
    ArgumentParser
    0.65
    Activations Density 0.017%

    No Known Activations