© 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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 5993
    Prev
    Next
    INDEX
    Explanations

    references to edges in a graph or network context

    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
    AndEndTag
    -0.89
    DockStyle
    -0.87
    GEBURTSDATUM
    -0.84
     propOrder
    -0.75
    SourceChecksum
    -0.74
     disambiguazione
    -0.73
    UIControlState
    -0.72
    Koordinaten
    -0.70
     متعلقه
    -0.68
    expandindo
    -0.66
    POSITIVE LOGITS
    edge
    1.02
    edges
    0.89
     Observation
    0.74
    су
    0.71
     observation
    0.70
    EDGE
    0.69
    Edge
    0.68
    Edges
    0.64
     Independence
    0.62
     edge
    0.60
    Activations Density 0.144%

    No Known Activations