© 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. 12293
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, keywords, and structures

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

    Java code or error logs

    np_acts-logits-general · gemini-2.0-flash

    Android Java code snippets

    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
    RenderAtEndOf
    -0.84
    AndEndTag
    -0.83
    DoubleQuotes
    -0.65
     BorderRadius
    -0.63
    \{\\
    -0.61
    databind
    -0.59
     PyLong
    -0.58
    FontOfSize
    -0.58
    ChildScrollView
    -0.58
    richTextPanel
    -0.57
    POSITIVE LOGITS
    TemporalType
    0.50
     Sant
    0.44
     Begle
    0.43
    Poloha
    0.41
     Мексичка
    0.41
    jsdelivr
    0.40
    Jereo
    0.39
    ActivityCompat
    0.39
    يميديا
    0.39
     тонн
    0.37
    Activations Density 0.050%

    No Known Activations