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. 12230
    Prev
    Next
    INDEX
    Explanations

    code snippets or references to file inclusions and source paths in programming contexts

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

    File paths or URLs

    np_acts-logits-general · gemini-2.0-flash

    relative file paths

    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
    principalColumn
    -0.71
     OMITBAD
    -0.64
    coroutines
    -0.61
    Spoljašnje
    -0.61
     onAnimation
    -0.61
    protoimpl
    -0.58
     useDispatch
    -0.57
     विश्वसनीयता
    -0.57
    ೌ
    -0.53
     mView
    -0.52
    POSITIVE LOGITS
    index
    1.05
     index
    0.88
    ../../
    0.86
    README
    0.85
    ../../../
    0.83
    ../
    0.76
     ../
    0.75
     README
    0.72
    Index
    0.69
    INDEX
    0.69
    Activations Density 0.196%

    No Known Activations