© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12178
    Prev
    Next
    INDEX
    Explanations

    phrases related to betrayal and deception

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

    Possessive "'s" or associated words

    np_acts-logits-general · gemini-2.0-flash

    assistants and subordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.66
    Демографія
    -0.65
    хьтан
    -0.60
    Autoritní
    -0.58
    
    -0.57
     propietarios
    -0.56
    BeginContext
    -0.56
    ंदीखरीदारी
    -0.55
     springfox
    -0.55
    Owner
    -0.53
    POSITIVE LOGITS
     assistants
    0.94
     hen
    0.94
     aides
    0.92
     minions
    0.89
     trusted
    0.86
     helpers
    0.85
     loyal
    0.83
     aide
    0.82
     cron
    0.78
     confid
    0.78
    Activations Density 0.332%

    No Known Activations