© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5058
    Prev
    Next
    INDEX
    Explanations

    references to religious texts, specifically those related to the priests and the laws of the Torah

    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
     Plin
    -0.64
     Sturgeon
    -0.62
     itſelf
    -0.61
     Astoria
    -0.60
     Jefus
    -0.57
     Diſ
    -0.57
     APE
    -0.57
     Astrid
    -0.57
     Monfieur
    -0.56
     Emper
    -0.55
    POSITIVE LOGITS
     Daniel
    0.82
     Israel
    0.79
     препратки
    0.76
    Daniel
    0.73
    hemiah
    0.72
     tartalomajánló
    0.72
     Israël
    0.72
    Israel
    0.70
    AndEndTag
    0.70
     Jeremiah
    0.69
    Activations Density 0.203%

    No Known Activations