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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 4
    Prev
    Next
    INDEX
    Explanations

    references to types of tiles and related construction materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VideoCapture
    -0.70
    antMatchers
    -0.53
    发表于
    -0.53
    唐
    -0.51
    ứ
    -0.51
    itor
    -0.51
     iload
    -0.49
     Kal
    -0.49
    binger
    -0.49
    ator
    -0.48
    POSITIVE LOGITS
    Hozzáférés
    0.71
     tile
    0.67
    StreetMap
    0.64
     marble
    0.63
    RunAsync
    0.63
    EndGlobalSection
    0.61
    PropertyChanging
    0.60
     lắm
    0.59
     sprocket
    0.58
    xaml
    0.57
    Activations Density 0.090%

    No Known Activations