© 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. 3-GEMMASCOPE-RES-16K
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    LaTeX structural commands, particularly for environments and mathematical constructs

    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
    ThroughAttribute
    -0.99
     lenker
    -0.92
     فريبيس
    -0.86
    libft
    -0.82
    IntoConstraints
    -0.81
    OGND
    -0.78
    BufferException
    -0.78
     mergeFrom
    -0.78
    addCriterion
    -0.77
    ########.
    -0.77
    POSITIVE LOGITS
     Brake
    0.58
    tabular
    0.53
     Jezus
    0.49
    <b>
    0.48
     Cupcakes
    0.47
    /**
    0.46
    if
    0.45
     probablement
    0.45
    ↵
    0.45
    <i>
    0.44
    Activations Density 0.055%

    No Known Activations