© 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. 14819
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate context, particularly temporal phrases or references to specific moments in time

    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
     HasFactory
    -0.68
    __;
    -0.59
     wonders
    -0.55
    eseorang
    -0.54
    seamnă
    -0.53
    thâu
    -0.52
    Diweddarwch
    -0.52
    withIdentifier
    -0.52
    ."],
    -0.51
    PRNewswire
    -0.51
    POSITIVE LOGITS
    ясь
    0.59
    cdnjs
    0.57
     During
    0.53
     Baillargeon
    0.53
     later
    0.52
    During
    0.51
     In
    0.51
    In
    0.50
     rare
    0.47
    IsContent
    0.46
    Activations Density 0.579%

    No Known Activations