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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 6324
    Prev
    Next
    INDEX
    Explanations

    terms related to biological inhibition mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.98
     autorytatywna
    -0.94
     itſelf
    -0.90
    sidemargin
    -0.84
    ^(@)
    -0.82
    ThroughAttribute
    -0.79
     Jefus
    -0.79
    ſelves
    -0.77
    Przypisy
    -0.76
     Theſe
    -0.76
    POSITIVE LOGITS
     inhibition
    0.94
     ban
    0.89
     Inhibition
    0.86
     dismissal
    0.78
     disable
    0.78
     shutdown
    0.78
     inhibit
    0.76
     inhibited
    0.76
     запре
    0.74
     inhibitory
    0.74
    Activations Density 3.167%

    No Known Activations