© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2458
    Prev
    Next
    INDEX
    Explanations

    terms related to accreditation and quality in professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.84
     purpoſe
    -0.81
     Theſe
    -0.80
     Jefus
    -0.72
     Monfieur
    -0.70
     ſtate
    -0.68
     reaſon
    -0.68
     poffible
    -0.66
     greateſt
    -0.65
     chng
    -0.64
    POSITIVE LOGITS
     certification
    2.24
     certified
    2.04
     certifications
    1.91
     Certification
    1.84
     Certified
    1.77
    certification
    1.74
     certifying
    1.72
    certified
    1.70
     certific
    1.69
    Certified
    1.65
    Activations Density 0.189%

    No Known Activations