© 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. 11-GEMMASCOPE-RES-16K
    11. 6392
    Prev
    Next
    INDEX
    Explanations

    instances of the word "create" and its variations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.84
    Personendaten
    -0.78
    CodedInputStream
    -0.77
    UnknownFields
    -0.74
    MessageTagHelper
    -0.73
    InSection
    -0.66
    PathVariable
    -0.65
     JScrollPane
    -0.64
    VersionUID
    -0.64
     onAnimation
    -0.63
    POSITIVE LOGITS
    create
    1.04
    Create
    0.92
    CREATE
    0.91
     Create
    0.84
    createNewFile
    0.81
     CREATE
    0.79
    createNew
    0.79
     创建
    0.79
     create
    0.79
     new
    0.73
    Activations Density 0.099%

    No Known Activations