© 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. 4-GEMMASCOPE-RES-16K
    6. 3984
    Prev
    Next
    INDEX
    Explanations

    words related to job opportunities and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.72
    TypedDataSet
    -0.70
    Chham
    -0.68
    DockStyle
    -0.68
     kasarigan
    -0.66
    rungsseite
    -0.65
    GeneratedMessage
    -0.65
     IconData
    -0.64
    upuncture
    -0.63
    AddTagHelper
    -0.62
    POSITIVE LOGITS
    */),
    0.58
     nubes
    0.46
     "));
    0.40
    ołnier
    0.40
     wearer
    0.40
     व्यक्ति
    0.39
     Địa
    0.39
     bew
    0.39
    щет
    0.39
    ";}
    0.38
    Activations Density 0.452%

    No Known Activations