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. 24-GEMMASCOPE-RES-16K
    6. 8397
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming logic and control structures

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

    arrays, elements, and indices

    np_acts-logits-general · gemini-2.0-flash

    elements in lists or arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.84
     BoxDecoration
    -0.80
    SequentialGroup
    -0.79
     InputDecoration
    -0.76
    FormTagHelper
    -0.74
    AutoField
    -0.74
     متعلقه
    -0.70
    WithIOException
    -0.69
    oa̍t
    -0.67
    MemoryWarning
    -0.67
    POSITIVE LOGITS
     element
    1.03
     value
    0.99
     elements
    0.91
     elemento
    0.88
     values
    0.87
    元素
    0.84
    element
    0.84
     valeur
    0.84
    value
    0.83
     elementos
    0.82
    Activations Density 0.651%

    No Known Activations