© 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. 16-GEMMASCOPE-RES-16K
    11. 4465
    Prev
    Next
    INDEX
    Explanations

    notational elements and mathematical expressions

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

    Bold font marker

    np_acts-logits-general · gemini-2.0-flash

    mathematical vectors and variables

    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
     larmes
    -0.70
    MethodManager
    -0.65
    riched
    -0.64
    FunctionFlags
    -0.62
     Sprung
    -0.61
     bezeichneter
    -0.60
     Prim
    -0.59
    tabular
    -0.59
     recevrez
    -0.59
    AsUp
    -0.58
    POSITIVE LOGITS
    mathbf
    0.86
    :+:
    0.59
     vectors
    0.56
    ARGB
    0.56
     Dvor
    0.55
     uninsured
    0.54
    Patterns
    0.53
    Демографія
    0.52
     IActionResult
    0.52
     harden
    0.52
    Activations Density 0.389%

    No Known Activations