Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13116
    Prev
    Next
    INDEX
    Explanations

    instances of the word "close" and its variations related to closure or shutting down

    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
     AssemblyProduct
    -0.95
    AppMethodBeat
    -0.83
    QMetaType
    -0.81
     CreateTagHelper
    -0.80
    WireFormatLite
    -0.80
    ècie
    -0.77
     façons
    -0.75
    mtext
    -0.74
     Brandt
    -0.74
     Berries
    -0.71
    POSITIVE LOGITS
     closed
    1.55
     Closed
    1.47
     closes
    1.46
     clos
    1.44
    Closed
    1.38
     closing
    1.30
     CLOSED
    1.26
     CLOS
    1.26
     Closes
    1.22
     Closing
    1.21
    Activations Density 0.078%

    No Known Activations