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

    Neuronpedia

    Jacobian LensNEW
    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. 15461
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual cleansing and redemption

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

    sin and repentance

    np_acts-logits-general · gemini-2.0-flash

    sin and guilt

    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
    rillas
    -0.62
     vedette
    -0.60
    rungsseite
    -0.59
     unanimous
    -0.58
    SequentialGroup
    -0.58
     Ruhm
    -0.57
     ovation
    -0.56
    Appellee
    -0.56
    ConstraintMaker
    -0.55
    afficheront
    -0.54
    POSITIVE LOGITS
     sin
    1.23
     sins
    1.21
     sinners
    1.04
     sinful
    0.96
     sinner
    0.96
     pecado
    0.95
    sin
    0.90
     guilt
    0.89
     pecados
    0.89
     sinned
    0.88
    Activations Density 0.149%

    No Known Activations