© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11071
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and interactions in the context of social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.93
     whoſe
    -0.88
     ſeveral
    -0.83
     Majefty
    -0.81
     themſelves
    -0.80
     myſelf
    -0.75
     Jefus
    -0.74
     quæ
    -0.74
     ſta
    -0.73
     ſy
    -0.72
    POSITIVE LOGITS
     dont
    1.29
     didnt
    1.15
     wasnt
    1.06
     Dont
    1.05
     isnt
    1.05
     doesnt
    1.05
     cant
    1.04
     arent
    1.03
     havent
    1.01
     DONT
    0.99
    Activations Density 0.609%

    No Known Activations