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. 20-GEMMASCOPE-RES-16K
    6. 1312
    Prev
    Next
    INDEX
    Explanations

    structured addresses and location information

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

    Room numbers and floor locations

    np_acts-logits-general · gemini-2.0-flash

    room or suite numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خصة
    -0.65
    PhysRev
    -0.61
    })),
    -0.49
    Архівовано
    -0.46
    gest
    -0.45
     contribué
    -0.45
    Revenir
    -0.44
    ExceptionHandler
    -0.44
     moschino
    -0.44
    __()
    -0.43
    POSITIVE LOGITS
     Unit
    0.89
    Unit
    0.84
     Bldg
    0.83
     UNIT
    0.82
     Room
    0.81
     SUITE
    0.78
     Suite
    0.77
    Room
    0.75
     Units
    0.74
    Suite
    0.74
    Activations Density 0.083%

    No Known Activations