© 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. 15001
    Prev
    Next
    INDEX
    Explanations

    themes of moral and ethical considerations, particularly related to treatment and respect for individuals

    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
     abbond
    -0.47
    ease
    -0.46
     tropicales
    -0.45
    Fiche
    -0.45
     menghi
    -0.44
    อัน
    -0.44
     duly
    -0.42
     duidelijk
    -0.42
     pertinentes
    -0.42
     Meksiku
    -0.41
    POSITIVE LOGITS
     differently
    1.49
     autrement
    0.94
     diffé
    0.90
     Biôgrafia
    0.84
     anders
    0.84
     Differ
    0.81
     like
    0.80
    цездатний
    0.80
     similarly
    0.77
     wrong
    0.76
    Activations Density 0.590%

    No Known Activations