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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6648
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to styling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.78
     CreateTagHelper
    -0.71
    BeginContext
    -0.64
     الحره
    -0.62
    Inflater
    -0.59
    cidae
    -0.58
     distanciation
    -0.58
    numerusform
    -0.56
    adal
    -0.55
     grafts
    -0.55
    POSITIVE LOGITS
     BorderSide
    0.75
     BoxDecoration
    0.69
     BorderRadius
    0.68
    aarrggbb
    0.59
     ngoài
    0.57
     InputDecoration
    0.54
    borderBottom
    0.50
    Matte
    0.50
    strokeWidth
    0.49
     outlined
    0.47
    Activations Density 0.515%

    No Known Activations