© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15010
    Prev
    Next
    INDEX
    Explanations

    descriptions and classifications of species and ecological information related to specific environments

    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
    BeginContext
    -0.52
    庁
    -0.52
     MainAxisSize
    -0.52
     Externe
    -0.49
     ngọc
    -0.49
    layui
    -0.49
     Gate
    -0.48
    Gate
    -0.48
     iVar
    -0.48
     Fische
    -0.46
    POSITIVE LOGITS
     forests
    0.87
     forest
    0.84
     woodland
    0.82
     grassland
    0.81
     lowland
    0.81
     woodlands
    0.77
     forested
    0.77
     lowlands
    0.77
     scrub
    0.74
     steppe
    0.73
    Activations Density 0.333%

    No Known Activations