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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12523
    Prev
    Next
    INDEX
    Explanations

    mentions of health and nutrition-related issues

    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
     Asheville
    -0.62
     Bulgarian
    -0.58
    jeeling
    -0.56
     Donegal
    -0.52
     Balkans
    -0.52
     Homer
    -0.52
     Thessal
    -0.52
    ímp
    -0.51
    Espèce
    -0.51
    enerys
    -0.51
    POSITIVE LOGITS
     Saudi
    1.38
    Saudi
    1.23
     Riyadh
    1.22
     Sau
    1.14
     Arabia
    1.10
     Kingdom
    1.06
     kingdom
    1.01
    Sau
    0.96
     Saud
    0.95
     Jeddah
    0.95
    Activations Density 0.143%

    No Known Activations