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. 19-GEMMASCOPE-RES-16K
    6. 3432
    Prev
    Next
    INDEX
    Explanations

    references to biblical authority and teachings related to Christian practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.56
    AsUp
    -0.53
    SourceChecksum
    -0.53
     estimés
    -0.51
    ResumeLayout
    -0.51
    痴
    -0.51
     Collabor
    -0.50
    Nationalité
    -0.50
    URLException
    -0.50
     disambiguazione
    -0.50
    POSITIVE LOGITS
     menciona
    0.67
     verse
    0.64
     henvisninger
    0.63
     bedoeld
    0.63
     Normdatei
    0.62
    Verses
    0.61
    FieldDescriptor
    0.61
     troviamo
    0.61
     disebutkan
    0.60
     posteriores
    0.60
    Activations Density 0.191%

    No Known Activations