Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15985
    Prev
    Next
    INDEX
    Explanations

    concepts related to power dynamics and authority

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

    Follows nouns related to mythology or time

    np_acts-logits-general · gemini-2.0-flash

    celestial, ancient, fairy, god, Dan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sobra
    -0.63
     consigo
    -0.53
     suivantes
    -0.52
     références
    -0.51
     conforman
    -0.51
    ंदीखरीदारी
    -0.51
     procedere
    -0.49
     complémentaires
    -0.48
     suivants
    -0.47
     betreft
    -0.46
    POSITIVE LOGITS
     ſtate
    0.74
    
    0.72
    Portály
    0.70
     XNUMX
    0.69
    bewerken
    0.69
     Inſ
    0.68
     Мексичка
    0.67
     ſind
    0.67
    queryInterface
    0.65
     houſe
    0.65
    Activations Density 0.128%

    No Known Activations