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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9955
    Prev
    Next
    INDEX
    Explanations

    phrases related to salvation and forgiveness through faith in Jesus Christ

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

    Following possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    my personal lord and savior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monks
    -0.47
     Liban
    -0.47
    ()]);
    -0.43
    rupulous
    -0.42
     наме
    -0.42
    ')}}
    -0.42
     Riet
    -0.42
    ")]
    -0.42
    ęż
    -0.41
    })}
    -0.41
    POSITIVE LOGITS
     propOrder
    0.83
     NSCoder
    0.76
     ProtoMessage
    0.74
     salvation
    0.74
     ujednoznacz
    0.72
     lenker
    0.69
     الرياضيه
    0.69
    enumi
    0.69
    ỡng
    0.68
    ItemBackground
    0.67
    Activations Density 0.067%

    No Known Activations