© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27638
    Prev
    Next
    INDEX
    Explanations

    elements and operations related to data parsing and metadata processing in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    early modern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ുറ
    -0.46
     Bind
    -0.44
    asteroide
    -0.43
    сто
    -0.43
    Neb
    -0.43
    cak
    -0.40
    导
    -0.40
     quang
    -0.39
    kom
    -0.39
    стви
    -0.39
    POSITIVE LOGITS
     חיצוניים
    0.93
     estekak
    0.91
     beginnetje
    0.84
    Portale
    0.82
    StoreMessageInfo
    0.80
    AccessorTable
    0.79
     createSlice
    0.79
    tvguidetime
    0.79
    省市镇
    0.77
    tonode
    0.77
    Activations Density 0.149%

    No Known Activations