© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting various qualities and attributes of people and groups

    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
     utafitiHapana
    -0.58
     adulta
    -0.54
     CreateTagHelper
    -0.53
    AddTagHelper
    -0.49
     perguntas
    -0.49
     themſelves
    -0.47
    toThrow
    -0.47
    enfance
    -0.47
    smp
    -0.46
     nė
    -0.46
    POSITIVE LOGITS
     guys
    2.68
     guy
    2.68
    guys
    2.22
    guy
    2.08
    Guys
    2.00
     GUYS
    1.96
     dude
    1.96
     Guys
    1.94
     dudes
    1.92
     fella
    1.83
    Activations Density 0.230%

    No Known Activations