Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6494
    Prev
    Next
    INDEX
    Explanations

    Java Swing components and their imports

    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
    peño
    -0.73
     kasarigan
    -0.63
    ″]
    -0.61
     fédé
    -0.61
    /$',
    -0.60
     remercier
    -0.60
    ]$}
    -0.59
     hipó
    -0.58
    erà
    -0.58
    즘
    -0.57
    POSITIVE LOGITS
     Meksiku
    0.85
     htons
    0.68
    Попис
    0.68
    formik
    0.63
     perten
    0.59
    Responder
    0.58
    aarrggbb
    0.58
     ſi
    0.57
     cantilever
    0.56
     deſt
    0.55
    Activations Density 0.149%

    No Known Activations