© 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 - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8900
    Prev
    Next
    INDEX
    Explanations

    phrases discussing personal identity and the concept of belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.69
    :
    -0.65
    .
    -0.62
    ,
    -0.60
     
    -0.58
     when
    -0.56
    <eos>
    -0.56
    ↵
    -0.54
     that
    -0.53
     from
    -0.52
    POSITIVE LOGITS
     Roskov
    1.34
    parsedMessage
    1.25
     utafitiHapana
    1.14
     TextInputType
    1.12
    PreferredItem
    1.09
     فريبيس
    1.08
    BibitemShut
    1.05
     tfsi
    1.00
     мәкал
    0.99
     MainAxisSize
    0.98
    Activations Density 0.051%

    No Known Activations