Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28127
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers and codes related to data or accounts

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

    hexadecimal identifiers

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     CreateTagHelper
    -0.78
     uska
    -0.72
     ModelExpression
    -0.71
    adaptiveStyles
    -0.70
    клопе
    -0.67
     تضيفلها
    -0.67
     Majefty
    -0.66
     Diſ
    -0.64
    DOCTYPE
    -0.63
    IVEREF
    -0.62
    POSITIVE LOGITS
     estimés
    0.48
     opérateur
    0.46
    ország
    0.46
    Przypisy
    0.45
     lalu
    0.45
     része
    0.44
    olstadt
    0.44
     Ste
    0.43
    marvin
    0.43
    Referanser
    0.41
    Activations Density 0.020%

    No Known Activations