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. 6-GEMMASCOPE-RES-16K
    6. 6945
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts related to derivatives and powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aji
    -0.48
    alu
    -0.46
    tek
    -0.46
     مُعرِّف
    -0.45
     fast
    -0.43
    ra
    -0.43
    lists
    -0.43
     مر
    -0.42
     salaries
    -0.42
    liest
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.92
     Paglinawan
    0.81
    GEBURTSDATUM
    0.78
    SourceChecksum
    0.77
    ksikon
    0.77
     AssemblyProduct
    0.77
    NameInMap
    0.76
    InjectAttribute
    0.75
    цездатний
    0.75
    sizeCache
    0.74
    Activations Density 0.952%

    No Known Activations