© 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. 24-GEMMASCOPE-RES-16K
    11. 14667
    Prev
    Next
    INDEX
    Explanations

    coding elements and structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and XML-like structures

    np_acts-logits-general · gemini-2.0-flash

    XML/HTML closing tags or attribute endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}"></
    -0.57
    ValueStyle
    -0.56
    .​
    -0.55
    postValue
    -0.53
    </em>
    -0.51
     
    -0.51
    éli
    -0.50
     }}">
    -0.50
    ViewFeatures
    -0.49
     препратки
    -0.49
    POSITIVE LOGITS
    2.00
    1.78
    1.65
    1.60
    1.53
    1.48
    1.44
    1.43
    1.40
    1.32
    Activations Density 0.291%

    No Known Activations