© 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. 14002
    Prev
    Next
    INDEX
    Explanations

    snippets and structures related to programming or software 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
     addUser
    -0.66
     addItem
    -0.57
    writeFile
    -0.52
    addObject
    -0.52
     newItem
    -0.51
     adding
    -0.51
     дописавши
    -0.50
    addProduct
    -0.49
    addTask
    -0.48
    addUser
    -0.48
    POSITIVE LOGITS
     retrieve
    1.27
     retrieving
    1.19
     retrieves
    1.14
     Retrieve
    1.13
     retrieval
    1.09
     obtain
    1.06
     retrieved
    1.04
    获取
    1.04
     querying
    1.04
     obtaining
    1.02
    Activations Density 0.467%

    No Known Activations