© 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. 16-GEMMASCOPE-RES-16K
    11. 4100
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms associated with linear algebra and quantum mechanics

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

    Mathematical/physics notation or code

    np_acts-logits-general · gemini-2.0-flash

    function calls and technical terms

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    OTIC
    -0.57
    chromatic
    -0.51
    ]+=
    -0.50
    :+:
    -0.49
    
    -0.49
     Marin
    -0.49
     &=&
    -0.49
    }~
    -0.49
    delmi
    -0.48
    ingt
    -0.48
    POSITIVE LOGITS
     which
    0.93
    which
    0.87
     ModelExpression
    0.81
    InjectAttribute
    0.79
     AssemblyCulture
    0.74
     whose
    0.72
    whose
    0.72
     CreateTagHelper
    0.71
    ConstraintMaker
    0.68
     Taktlose
    0.67
    Activations Density 1.065%

    No Known Activations