© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12600
    Prev
    Next
    INDEX
    Explanations

    phrases related to accreditation and certification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jae
    -0.56
     inconn
    -0.56
    BorderLayout
    -0.52
    Referències
    -0.51
     неизвест
    -0.51
    Kjelder
    -0.51
     quietly
    -0.50
    RenderAtEndOf
    -0.50
     desconoc
    -0.49
    prnewswire
    -0.49
    POSITIVE LOGITS
     certified
    1.00
     Certified
    0.78
    certified
    0.77
     certification
    0.73
    Certified
    0.72
     designated
    0.66
    Hentet
    0.63
    Rhestr
    0.63
     approved
    0.61
     recognized
    0.61
    Activations Density 0.340%

    No Known Activations