© 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. 20-GEMMASCOPE-RES-16K
    11. 3939
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and functions associated with bio input/output operations

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

    BIO-related function calls and configurations

    np_acts-logits-general · gemini-2.0-flash

    memory management and data operations

    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
    veli
    -0.40
     millions
    -0.39
     phạm
    -0.38
     bites
    -0.38
    ↵
    -0.38
    ↵↵
    -0.37
     بیر
    -0.37
     hundreds
    -0.37
     jelent
    -0.37
     [
    -0.37
    POSITIVE LOGITS
    
    0.90
     الحره
    0.90
     ModelExpression
    0.90
    تقاوى
    0.89
     NSCoder
    0.81
    enderror
    0.77
    FieldBuilder
    0.76
     للاسماء
    0.76
    WriteAttribute
    0.76
    MethodManager
    0.75
    Activations Density 0.384%

    No Known Activations