© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4104
    Prev
    Next
    INDEX
    Explanations

    references to 'hell' and related negative concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osene
    -0.77
    UIControlState
    -0.76
     betweenstory
    -0.76
    vábbi
    -0.73
     Bourgoin
    -0.73
     uVar
    -0.71
     समीक्षक
    -0.71
    AnchorStyles
    -0.70
    nteral
    -0.70
    prüche
    -0.69
    POSITIVE LOGITS
     Hell
    1.34
     HELL
    1.28
     hell
    1.21
    Hell
    1.17
    hell
    1.05
     infierno
    1.02
    HELL
    1.02
    heaven
    0.94
     HEAVEN
    0.88
     Satan
    0.88
    Activations Density 0.064%

    No Known Activations