Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12347
    Prev
    Next
    INDEX
    Explanations

    military ranks and roles in the context of service members and their actions

    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
     utafitiHapana
    -0.61
     الرياضيه
    -0.56
    ]+=
    -0.52
    Mode
    -0.51
     Modem
    -0.51
     accelerators
    -0.50
     Ministers
    -0.50
    出版年
    -0.49
    jsdelivr
    -0.49
     Mode
    -0.49
    POSITIVE LOGITS
     Captain
    1.09
     captain
    1.05
     Lieutenant
    1.02
     Sergeant
    1.02
    Corpor
    0.99
    Captain
    0.99
     lieutenant
    0.98
     sergeant
    0.98
    Sergeant
    0.97
     corporal
    0.97
    Activations Density 0.311%

    No Known Activations