© 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. 3-GEMMASCOPE-RES-16K
    6. 15808
    Prev
    Next
    INDEX
    Explanations

    function calls related to retrieving or accessing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventName
    -0.77
     clearColor
    -0.76
     totalCount
    -0.72
     newItem
    -0.71
     Aun
    -0.70
    zension
    -0.70
    theless
    -0.69
    nein
    -0.68
     olun
    -0.68
     שוליים
    -0.68
    POSITIVE LOGITS
     get
    1.03
     GET
    0.75
     Get
    0.70
    Géographie
    0.60
     find
    0.60
     pop
    0.58
     create
    0.58
    jandra
    0.57
    Bissau
    0.57
    Jules
    0.56
    Activations Density 0.052%

    No Known Activations