© 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. 7242
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and formal relationships

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

    "as" followed by specific function/syntax-related words

    np_acts-logits-general · gemini-2.0-flash

    as ... orthogonal, specialization, average

    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
    ContentAsync
    -0.56
    adaptiveStyles
    -0.54
     agrí
    -0.52
     للمعارف
    -0.50
     TextInputType
    -0.49
    EnableWeb
    -0.49
    intur
    -0.48
    IndentedString
    -0.47
     Irrit
    -0.45
     Teg
    -0.45
    POSITIVE LOGITS
    PARATUS
    0.66
    featureID
    0.64
    _
    0.61
    '},
    0.60
     SwitchCompat
    0.59
     prostu
    0.59
    ցված
    0.58
     protoimpl
    0.54
    IENTS
    0.54
    jenige
    0.54
    Activations Density 1.294%

    No Known Activations