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. 10-GEMMASCOPE-RES-16K
    6. 13457
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     señores
    -0.43
     méthode
    -0.38
    暴
    -0.37
     ilmo
    -0.36
     tulee
    -0.36
    method
    -0.36
     jugo
    -0.35
     pertinentes
    -0.35
     কর
    -0.35
     faites
    -0.34
    POSITIVE LOGITS
    yntaxException
    0.78
    Хьажоргаш
    0.77
    verwijspagina
    0.76
    MemoryWarning
    0.76
     مرئيه
    0.72
    MLLoader
    0.72
     AssemblyTitle
    0.72
    expandindo
    0.71
    endforeach
    0.70
    findpost
    0.69
    Activations Density 0.181%

    No Known Activations