© 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. 15-GEMMASCOPE-RES-16K
    11. 1232
    Prev
    Next
    INDEX
    Explanations

    references to varying types of services and conditions in clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemLayout
    -0.51
     yeux
    -0.45
     fatti
    -0.45
     responsáveis
    -0.45
     nœ
    -0.44
    AddTagHelper
    -0.43
    ̍t
    -0.43
    brainer
    -0.43
    AfterClass
    -0.43
     faltar
    -0.43
    POSITIVE LOGITS
     types
    1.08
     different
    1.01
     modes
    0.88
    different
    0.88
     Types
    0.88
     Different
    0.87
     styles
    0.86
    Different
    0.86
     unterschied
    0.84
     depending
    0.83
    Activations Density 0.527%

    No Known Activations