© 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. 2-GEMMASCOPE-RES-16K
    11. 14885
    Prev
    Next
    INDEX
    Explanations

    references to "new" concepts, developments, or innovations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.73
     Wiktionnaire
    -0.63
    UrlResolution
    -0.62
     parcour
    -0.62
     tetanus
    -0.59
     Maruti
    -0.58
    oa̍t
    -0.58
     HttpNotFound
    -0.58
     Suresh
    -0.57
    achella
    -0.56
    POSITIVE LOGITS
     new
    0.96
     nueva
    0.88
     neuen
    0.84
    新的
    0.84
     nieuwe
    0.81
     nuevos
    0.81
     νέ
    0.79
     nuevas
    0.78
     nuovi
    0.75
     nouvelles
    0.74
    Activations Density 0.214%

    No Known Activations