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. 5-GEMMASCOPE-RES-16K
    6. 3987
    Prev
    Next
    INDEX
    Explanations

    doctrinal terms and their recognition within religious or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neceffary
    -0.58
     purpoſe
    -0.58
    zieży
    -0.56
    
    -0.56
    DebuggerNonUser
    -0.56
     preſent
    -0.54
     houſe
    -0.54
    ícios
    -0.54
    kespea
    -0.53
     <=",
    -0.53
    POSITIVE LOGITS
     doctrines
    0.96
     doctrine
    0.89
     theories
    0.84
     dogma
    0.82
     concepts
    0.78
     theory
    0.75
     tenets
    0.73
     teori
    0.73
     doctrina
    0.71
    doctrine
    0.68
    Activations Density 0.710%

    No Known Activations