© 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. 12211
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in code

    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
     <>",
    -0.83
    LookAnd
    -0.74
    InvalidProtocol
    -0.69
     kasarigan
    -0.68
     виправивши
    -0.66
    ंदीखरीदारी
    -0.64
    SerializedSize
    -0.64
    ьаж
    -0.63
    OrBuilder
    -0.62
    NUMX
    -0.61
    POSITIVE LOGITS
    гава
    0.63
     consequently
    0.60
     Consequently
    0.57
     therefore
    0.56
     quindi
    0.54
     donc
    0.53
     Instead
    0.53
     hence
    0.53
    instead
    0.51
     instead
    0.51
    Activations Density 0.052%

    No Known Activations