© 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. 10-GEMMASCOPE-RES-16K
    6. 15234
    Prev
    Next
    INDEX
    Explanations

    references to dictionaries and related data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chargez
    -0.85
    kfree
    -0.75
    SEVERE
    -0.75
     seaborn
    -0.72
    graves
    -0.72
    oughly
    -0.71
     strtotime
    -0.71
    endphp
    -0.71
    execu
    -0.69
    wnie
    -0.69
    POSITIVE LOGITS
     dictionary
    1.21
    dict
    1.19
    Dict
    1.19
     dict
    1.16
     Dict
    1.16
     dictionaries
    1.15
     Dictionaries
    1.09
     Dictionary
    1.06
    Dictionary
    1.04
    DICT
    1.01
    Activations Density 0.114%

    No Known Activations