© 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. 2-GEMMASCOPE-RES-16K
    6. 1504
    Prev
    Next
    INDEX
    Explanations

    terms related to legal procedures and evidence

    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
    BufferException
    -0.94
     propOrder
    -0.88
    RectangleBorder
    -0.85
     Theſe
    -0.85
     Majefty
    -0.84
    glGen
    -0.82
     Efq
    -0.82
     becauſe
    -0.81
     ویکی‌پدیا
    -0.81
     leaſt
    -0.80
    POSITIVE LOGITS
    ⓧ
    0.59
     så
    0.52
     }^{[
    0.44
    g
    0.42
    -(
    0.42
    ....
    0.41
    ">'.$
    0.41
    ;
    0.41
     spécifiques
    0.40
    ristown
    0.40
    Activations Density 0.365%

    No Known Activations