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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 2879
    Prev
    Next
    INDEX
    Explanations

    mentions of algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queline
    -0.86
    jacke
    -0.64
    ===
    -0.64
    हो
    -0.64
     Obl
    -0.62
    bA
    -0.59
    a
    -0.59
     Cus
    -0.58
     Shand
    -0.58
     Brice
    -0.58
    POSITIVE LOGITS
     algorithm
    2.01
     algorithms
    1.98
     Algorithm
    1.92
     Algorithms
    1.87
    algorithm
    1.81
    Algorithm
    1.80
    GORITHM
    1.66
    orithmic
    1.58
    算法
    1.55
     algorit
    1.54
    Activations Density 0.083%

    No Known Activations