© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4804
    Prev
    Next
    INDEX
    Explanations

    specific property attributes or identifiers associated with data structures or objects

    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
     فريبيس
    -0.57
    rizona
    -0.52
     culturali
    -0.51
     División
    -0.50
     Cách
    -0.49
    ableness
    -0.47
    pegno
    -0.47
    kään
    -0.47
     variety
    -0.47
     onOptions
    -0.47
    POSITIVE LOGITS
     resourceCulture
    0.80
    SuppressMessage
    0.70
    complexContent
    0.69
    ParallelGroup
    0.63
    HideFlags
    0.63
    TypedDataSet
    0.62
    TagMode
    0.58
    Демографія
    0.58
     Exacts
    0.58
    SequentialGroup
    0.57
    Activations Density 3.043%

    No Known Activations