© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11943
    Prev
    Next
    INDEX
    Explanations

    phrases relating to time predictions and evaluations

    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
    aarrggbb
    -0.56
    mphony
    -0.47
     newItem
    -0.46
     urma
    -0.45
    atoday
    -0.45
    Bibliografía
    -0.44
    Демографія
    -0.44
    قایناق‌لار
    -0.43
    abab
    -0.42
    şim
    -0.42
    POSITIVE LOGITS
    LookAnd
    0.64
     closer
    0.61
    もっと
    0.59
    AndroidJUnit
    0.58
     réalité
    0.58
    unehmen
    0.56
    PushMatrix
    0.56
     nearer
    0.56
     actually
    0.55
     Closer
    0.54
    Activations Density 0.580%

    No Known Activations