© 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. 21-GEMMASCOPE-RES-16K
    11. 2581
    Prev
    Next
    INDEX
    Explanations

    Japanese characters and their associations with names and locations

    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
     
    -1.02
    ,
    -0.90
     O
    -0.86
     (
    -0.85
     G
    -0.83
     "
    -0.80
     V
    -0.79
     E
    -0.79
     to
    -0.79
     +
    -0.79
    POSITIVE LOGITS
     Efq
    2.00
     myſelf
    1.99
     ―――――
    1.94
     Theſe
    1.92
     doubtnut
    1.89
     photolibrary
    1.86
     pleaſure
    1.85
     itſelf
    1.82
     Monfieur
    1.82
     ſind
    1.82
    Activations Density 0.085%

    No Known Activations