© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14566
    Prev
    Next
    INDEX
    Explanations

    numerical data and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.75
    发表于
    -0.75
    Amicalement
    -0.68
    ględ
    -0.67
    ніципалі
    -0.62
    RenderAtEndOf
    -0.62
    πάρχ
    -0.61
     CreateTagHelper
    -0.60
     getNome
    -0.60
    Бахар
    -0.59
    POSITIVE LOGITS
     Galileo
    0.51
    StateList
    0.47
    häng
    0.44
    隙
    0.44
    RELATED
    0.44
     night
    0.44
     gynnwys
    0.43
    SOUNDBITE
    0.43
     vítima
    0.42
    s
    0.42
    Activations Density 0.008%

    No Known Activations