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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 39277
    Prev
    Next
    INDEX
    Explanations

    elements that indicate a legal or formal context, especially within metadata or citation formats

    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
    SharedCtor
    -0.86
     CreateTagHelper
    -0.80
    Personendaten
    -0.78
    astéro
    -0.75
    archiviato
    -0.72
     propOrder
    -0.71
     bezeichneter
    -0.69
    sizeCache
    -0.69
     Савезне
    -0.66
    webElementXpaths
    -0.64
    POSITIVE LOGITS
    Enllaces
    0.60
     خارجية
    0.53
    ########.
    0.52
    contentLoaded
    0.51
    bewerken
    0.50
    }-${
    0.48
     CGFloat
    0.47
     Signalez
    0.47
    urgia
    0.45
     RISERVATA
    0.43
    Activations Density 0.223%

    No Known Activations