© 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. 14596
    Prev
    Next
    INDEX
    Explanations

    variable-length identifiers or terms that start with uppercase letters

    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
    yny
    -0.49
     leng
    -0.49
    y
    -0.48
     senti
    -0.47
    chere
    -0.46
    יג
    -0.45
     identi
    -0.45
     Oester
    -0.45
    vill
    -0.44
    onomy
    -0.44
    POSITIVE LOGITS
    +#+#
    1.07
     kasarigan
    0.96
    ThroughAttribute
    0.95
     متعلقه
    0.86
    HomeAsUpEnabled
    0.86
    Przypisy
    0.85
    InSection
    0.83
     مشين
    0.83
    jsonwebtoken
    0.83
    ChildScrollView
    0.83
    Activations Density 0.213%

    No Known Activations