© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 14142
    Prev
    Next
    INDEX
    Explanations

    various forms of code block structures and their closures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bronnen
    -0.59
    __(/*!
    -0.55
    GeneratedCode
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    phosa
    -0.52
    通販
    -0.52
     fata
    -0.51
    ahul
    -0.50
     Creo
    -0.50
     lampa
    -0.49
    POSITIVE LOGITS
    angerie
    0.63
     cherchés
    0.56
    JvmStatic
    0.54
    osexuality
    0.52
    StoryboardSegue
    0.52
     Wikimedijinoj
    0.51
    ngiliz
    0.50
     gynhyrchwyd
    0.50
    ifrance
    0.50
    UnsafeEnabled
    0.50
    Activations Density 0.090%

    No Known Activations