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. 16-GEMMASCOPE-RES-16K
    6. 1728
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and scripture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with faith/religion

    np_acts-logits-general · gemini-2.0-flash

    religious and moral teachings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ins
    -0.51
     w
    -0.49
     too
    -0.49
     le
    -0.48
     “
    -0.48
    vey
    -0.47
    度
    -0.47
    PI
    -0.47
    conci
    -0.46
     fe
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    1.03
    ViewFeatures
    0.90
     mxArray
    0.86
     GenerationType
    0.86
    хьтан
    0.85
     ComVisible
    0.82
    contentLoaded
    0.82
     <>",
    0.82
    SBATCH
    0.80
    principalTable
    0.80
    Activations Density 0.131%

    No Known Activations