© 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. 4-GEMMASCOPE-RES-16K
    11. 1034
    Prev
    Next
    INDEX
    Explanations

    words related to roles, titles, and positions within organizations or groups

    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
    ViewFeatures
    -0.94
    ThroughAttribute
    -0.93
     للمعارف
    -0.89
     BrowserModule
    -0.87
    Vidite
    -0.87
     doInBackground
    -0.85
     estimés
    -0.84
    ^(@)
    -0.83
    SequentialGroup
    -0.81
    #
    -0.81
    POSITIVE LOGITS
     who
    0.84
     people
    0.70
     whom
    0.66
     personne
    0.64
    who
    0.64
    people
    0.59
     personnes
    0.59
     person
    0.58
     người
    0.55
     persone
    0.54
    Activations Density 1.558%

    No Known Activations