© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11579
    Prev
    Next
    INDEX
    Explanations

    references to "bull sharks."

    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
    Jereo
    -0.75
     Rev
    -0.74
    Бахар
    -0.70
    PyExc
    -0.69
     androidx
    -0.68
    IndentedString
    -0.68
    Rev
    -0.68
    GeneratedCode
    -0.67
    nologies
    -0.66
     تضيفلها
    -0.66
    POSITIVE LOGITS
     stub
    1.70
    stub
    1.28
     Stub
    1.24
    Stub
    1.15
     stubs
    1.12
     bull
    0.93
    iostream
    0.91
     BULL
    0.87
     Bull
    0.82
    bull
    0.82
    Activations Density 0.011%

    No Known Activations