© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2314
    Prev
    Next
    INDEX
    Explanations

    historical figures and their roles in military or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.71
     Centa
    -0.69
     Mero
    -0.66
     Efq
    -0.65
     Majefty
    -0.63
    ệc
    -0.61
     Lati
    -0.60
     itſelf
    -0.60
     Sylvie
    -0.59
     Canto
    -0.59
    POSITIVE LOGITS
    MemoryWarning
    0.58
    Statistiche
    0.53
     pendapat
    0.52
    SharedCtor
    0.51
    Kanada
    0.51
     Púb
    0.48
    évaluateur
    0.48
     tribus
    0.47
    Дереккөздер
    0.47
     demnach
    0.46
    Activations Density 0.194%

    No Known Activations