© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10493
    Prev
    Next
    INDEX
    Explanations

    terms related to "subject" and its various usages in the text

    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
     SPS
    -0.84
     GenerationType
    -0.71
    ForRow
    -0.71
    csolódó
    -0.70
     CNP
    -0.70
     Hogarth
    -0.69
     membuk
    -0.69
    infinity
    -0.67
     fidelity
    -0.67
     GAC
    -0.66
    POSITIVE LOGITS
     subject
    3.25
    subject
    2.99
     Subject
    2.98
    Subject
    2.85
     subjects
    2.80
     SUBJECT
    2.74
     Subjects
    2.61
    SUBJECT
    2.56
    subjects
    2.43
    Subjects
    2.34
    Activations Density 0.059%

    No Known Activations