© 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. 21-GEMMASCOPE-RES-16K
    11. 1381
    Prev
    Next
    INDEX
    Explanations

    PHP function definitions related to user management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.44
    Према
    -0.39
     đừng
    -0.36
     conveyed
    -0.35
     nø
    -0.35
     impressed
    -0.35
    xmlns
    -0.35
    ussen
    -0.35
     recombinant
    -0.34
    解釈
    -0.34
    POSITIVE LOGITS
     edit
    1.82
     Edit
    1.65
     editing
    1.54
    edit
    1.54
    Edit
    1.46
     Editing
    1.35
     EDIT
    1.33
     edits
    1.29
    EDIT
    1.22
    编辑
    1.20
    Activations Density 0.208%

    No Known Activations