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. 16-GEMMASCOPE-RES-16K
    6. 4974
    Prev
    Next
    INDEX
    Explanations

    references to theatrical productions or adaptations related to literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "theatre" or "theater"

    np_acts-logits-general · gemini-2.0-flash

    theatre and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppMethodBeat
    -0.61
    UnknownFields
    -0.60
    \{\\
    -0.57
    makeConstraints
    -0.54
    writeFieldEnd
    -0.53
     UIColor
    -0.52
     ActionListener
    -0.51
     disambiguazione
    -0.51
    UnifiedTopology
    -0.51
    PyExc
    -0.51
    POSITIVE LOGITS
     theatre
    1.29
     theater
    1.28
     Theatre
    1.19
     theatrical
    1.17
     Theater
    1.16
     theatres
    1.11
    Theatre
    1.10
    theatre
    1.09
    Theater
    1.08
     theaters
    1.06
    Activations Density 0.151%

    No Known Activations