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. 21-GEMMASCOPE-RES-16K
    6. 8373
    Prev
    Next
    INDEX
    Explanations

    codes and structures related to iterators and collections in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.69
    MemoryWarning
    -0.65
     protoimpl
    -0.56
     resourceCulture
    -0.56
    榄
    -0.54
     chalk
    -0.53
     correctes
    -0.52
    enderror
    -0.50
    aliyun
    -0.50
     Basque
    -0.48
    POSITIVE LOGITS
     iterator
    1.41
     Iterator
    1.31
    Iterator
    1.26
    iterator
    1.25
     iter
    1.20
     GetEnumerator
    1.16
    iter
    1.09
     iterate
    1.03
    iterate
    1.02
    迭代
    1.02
    Activations Density 0.288%

    No Known Activations