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. 25-GEMMASCOPE-RES-16K
    6. 8587
    Prev
    Next
    INDEX
    Explanations

    references to religious institutions and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.62
    aryen
    -0.58
     Audiodateien
    -0.56
     Religion
    -0.54
    iedene
    -0.53
     bezeichneter
    -0.52
    suya
    -0.52
    openhauer
    -0.52
    yarnpkg
    -0.52
     religi
    -0.51
    POSITIVE LOGITS
     Patriarch
    0.78
     métro
    0.77
     Metropolitan
    0.75
     metropol
    0.72
    Metropolitan
    0.70
     icons
    0.69
     Icons
    0.67
     Metropol
    0.66
     icon
    0.66
     patriarch
    0.65
    Activations Density 0.157%

    No Known Activations