© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    certifications and regulatory statuses related to professional licenses and institutions

    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
    CodedInputStream
    -0.53
     rowspan
    -0.48
    mai
    -0.46
    ynen
    -0.43
    pidou
    -0.43
    panier
    -0.43
     man
    -0.42
    SEVERE
    -0.41
    >*/
    -0.41
    rider
    -0.41
    POSITIVE LOGITS
     certified
    1.06
    certified
    0.95
     certification
    0.93
    astify
    0.87
    Certified
    0.87
     Certified
    0.86
    Rhestr
    0.81
     accredited
    0.80
     certifications
    0.79
     Certification
    0.77
    Activations Density 0.170%

    No Known Activations