© 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. 10-GEMMASCOPE-RES-16K
    11. 5990
    Prev
    Next
    INDEX
    Explanations

    instances of the term "clone" and its derivatives in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.54
     tenues
    -0.50
    variable
    -0.50
    JMenuBar
    -0.50
    mittel
    -0.49
    ngua
    -0.48
    complexContent
    -0.48
    bundet
    -0.48
    FXML
    -0.47
     rendus
    -0.46
    POSITIVE LOGITS
    deepcopy
    1.05
    arraycopy
    1.00
     deepcopy
    0.98
     copying
    0.97
     copy
    0.96
    Copied
    0.94
     clone
    0.94
     copied
    0.93
     shutil
    0.92
    copy
    0.92
    Activations Density 0.229%

    No Known Activations