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. 22-GEMMASCOPE-RES-16K
    6. 3472
    Prev
    Next
    INDEX
    Explanations

    elements of code related to testing functions and their properties in a programming context

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

    Code related to testing and descriptions

    np_acts-logits-general · gemini-2.0-flash

    describe and it tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.66
    DoubleQuotes
    -0.62
    DrawerToggle
    -0.59
    Искәрмәләр
    -0.59
     skak
    -0.58
    TagHelper
    -0.57
    contentLoaded
    -0.56
    estacks
    -0.54
    RepeatedField
    -0.54
     CWE
    -0.54
    POSITIVE LOGITS
    describe
    0.70
     describe
    0.69
    it
    0.62
    xit
    0.61
    context
    0.56
    ++);
    0.55
     describes
    0.49
    Jegyzetek
    0.49
    acme
    0.48
    Describe
    0.48
    Activations Density 0.123%

    No Known Activations