© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8380
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data management

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

    Software functionality/modules

    np_acts-logits-general · gemini-2.0-flash

    security and system components

    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
     themſelves
    -0.78
     becauſe
    -0.78
     himſelf
    -0.77
     actuels
    -0.73
     aussitôt
    -0.72
     myſelf
    -0.72
     appartiennent
    -0.72
     quelcon
    -0.71
     africains
    -0.71
     détruit
    -0.70
    POSITIVE LOGITS
     mode
    0.88
     functionality
    0.71
     management
    0.69
     feature
    0.68
     mechanism
    0.67
     control
    0.66
     support
    0.65
     modes
    0.64
     module
    0.64
     information
    0.63
    Activations Density 1.180%

    No Known Activations