© 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. 20-GEMMASCOPE-RES-16K
    11. 14960
    Prev
    Next
    INDEX
    Explanations

    characters related to conflict and betrayal in narratives

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

    Kyuranger storyline and characters

    np_acts-logits-general · gemini-2.0-flash

    betrayal and revenge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.53
    }],
    -0.52
     fono
    -0.49
    érons
    -0.49
     Vikipedi
    -0.49
    商务
    -0.49
     bibl
    -0.48
     locally
    -0.48
     ")");
    -0.47
    侃
    -0.47
    POSITIVE LOGITS
     betrayed
    0.76
     betray
    0.73
     humanity
    0.71
     revenge
    0.71
     betrayal
    0.70
     betraying
    0.70
     missions
    0.70
     protecting
    0.67
     sacrifice
    0.66
     avenge
    0.66
    Activations Density 0.519%

    No Known Activations