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. 15-GEMMASCOPE-RES-16K
    6. 12697
    Prev
    Next
    INDEX
    Explanations

    function calls and their associated parameters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Karakteristik
    -0.53
     business
    -0.53
     Lu
    -0.52
     Den
    -0.49
    izin
    -0.47
     lu
    -0.47
    protoc
    -0.47
     base
    -0.46
     parent
    -0.46
     wo
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.83
     صوتيه
    0.81
     africaine
    0.80
     termica
    0.79
    twimg
    0.77
     Савезне
    0.75
    initComponents
    0.74
    setVerticalGroup
    0.71
     AssemblyCulture
    0.68
    ंदीखरीदारी
    0.67
    Activations Density 0.122%

    No Known Activations