© 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. 3-GEMMASCOPE-RES-16K
    11. 5914
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of brackets and braces, particularly in mathematical expressions or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mandela
    -0.62
    bakken
    -0.59
     har
    -0.58
    ist
    -0.58
     mati
    -0.58
    isto
    -0.58
    iegel
    -0.57
     looks
    -0.57
     nó
    -0.56
     déb
    -0.55
    POSITIVE LOGITS
    }{
    2.37
    )}{
    1.70
     }{
    1.57
    ]}{
    1.51
    }}{
    1.49
    |}{
    1.43
    {}{
    1.37
    }}}{
    1.24
    }{\
    1.24
    )}}{
    1.22
    Activations Density 0.184%

    No Known Activations