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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12364
    Prev
    Next
    INDEX
    Explanations

    technical terms related to functionality and performance issues in devices or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.62
    mybatisplus
    -0.56
     AssemblyProduct
    -0.55
     المعيارى
    -0.51
    BeginContext
    -0.48
    ására
    -0.47
    üman
    -0.45
    sidemargin
    -0.45
    PyExc
    -0.43
    intios
    -0.43
    POSITIVE LOGITS
     functioning
    2.32
     working
    2.22
    functioning
    1.92
    working
    1.90
    Working
    1.82
     Working
    1.82
     WORKING
    1.78
    WORKING
    1.75
     function
    1.71
     functional
    1.70
    Activations Density 0.622%

    No Known Activations