© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 101134
    Prev
    Next
    INDEX
    Explanations

    terms related to sin and guilt in a religious context

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

    sin and sins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.59
     Regard
    -0.56
    ◄
    -0.54
    __':
    -0.53
     للمعارف
    -0.52
    .*")]
    -0.49
    >-->
    -0.49
    PullParser
    -0.47
    hamad
    -0.46
    èvres
    -0.45
    POSITIVE LOGITS
     sins
    1.13
     sin
    0.98
     pecado
    0.97
     pecados
    0.94
     sinned
    0.92
     Sünde
    0.88
     Sünden
    0.87
     Sins
    0.84
     sinful
    0.81
     sinner
    0.75
    Activations Density 0.012%

    No Known Activations