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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1699
    Prev
    Next
    INDEX
    Explanations

    terms related to digital rights and content management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voulais
    -0.52
    Ђ
    -0.51
     ffilmiau
    -0.51
     biodegradable
    -0.49
    ylase
    -0.49
     spilled
    -0.49
    inga
    -0.49
     مشين
    -0.47
     neutre
    -0.47
     جات
    -0.47
    POSITIVE LOGITS
    Rohy
    0.64
    autorest
    0.64
    onViewCreated
    0.58
    InjectAttribute
    0.57
     Resmi
    0.56
     smtplib
    0.55
    archiviato
    0.55
    Datuak
    0.52
     ***!
    0.52
    online
    0.51
    Activations Density 0.451%

    No Known Activations