© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5415
    Prev
    Next
    INDEX
    Explanations

    functional programming patterns related to data manipulation

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

    LINQ-style queries and operations

    np_acts-logits-general · gemini-2.0-flash

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     whiteColor
    -0.59
    外部リンク
    -0.56
     CreateTagHelper
    -0.54
    FormTagHelper
    -0.52
    '}}>
    -0.52
     Division
    -0.52
    prüche
    -0.51
    
    -0.50
     ?>">
    -0.49
     transfieras
    -0.49
    POSITIVE LOGITS
    delegate
    0.71
     Elisha
    0.61
     delegate
    0.58
    ilanth
    0.56
    ISupport
    0.55
    lijken
    0.54
     lambda
    0.54
    vency
    0.52
     barefoot
    0.52
    JoinTable
    0.51
    Activations Density 0.111%

    No Known Activations