© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10383
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to morality, particularly the interplay of good and evil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     صوتيه
    -0.56
    HasForeignKey
    -0.50
    contentLoaded
    -0.50
    IntoConstraints
    -0.50
    DllImport
    -0.46
    principalTable
    -0.46
    mybatisplus
    -0.46
    --}}
    -0.46
    __(/*!
    -0.45
     Spass
    -0.45
    POSITIVE LOGITS
     evil
    0.92
    Evil
    0.89
    evil
    0.83
     Evil
    0.83
     good
    0.80
    good
    0.78
    Good
    0.76
     Good
    0.76
     evils
    0.73
     GOOD
    0.71
    Activations Density 0.342%

    No Known Activations