© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1327
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    labelledby
    -0.67
    +#+#
    -0.65
     InputDecoration
    -0.65
     références
    -0.63
    NOPQRST
    -0.61
    #+#
    -0.60
     BoxFit
    -0.57
    ="@+
    -0.56
    ßten
    -0.55
    ITARY
    -0.55
    POSITIVE LOGITS
    ${
    1.15
    <bos>
    0.73
    \|_{
    0.72
    PerformLayout
    0.70
    RegressionTest
    0.63
    RefNanny
    0.62
     ProtoMessage
    0.61
    \|_{\
    0.60
    AddressBook
    0.57
    )))));
    0.56
    Activations Density 0.096%

    No Known Activations