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. 9-GEMMASCOPE-RES-16K
    6. 9209
    Prev
    Next
    INDEX
    Explanations

    terms related to approximation and estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     songs
    -0.57
     sen
    -0.55
    o
    -0.54
    希
    -0.53
     ngừa
    -0.53
     fullt
    -0.50
    ola
    -0.50
     den
    -0.49
    rmtree
    -0.49
    stry
    -0.49
    POSITIVE LOGITS
     approxim
    1.36
     approximate
    1.31
     Approximate
    1.28
     approximated
    1.27
    approximate
    1.22
     approx
    1.22
     Approx
    1.21
    Approx
    1.18
     Approximation
    1.18
     approximation
    1.18
    Activations Density 0.211%

    No Known Activations