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. 4420
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and connections in a digital context

    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
         
    -0.46
    Continue
    -0.46
    ThroughAttribute
    -0.45
                                   
    -0.45
     AutoMapper
    -0.43
    指示
    -0.42
    драт
    -0.41
                
    -0.41
    EDIA
    -0.41
          
    -0.41
    POSITIVE LOGITS
     Efq
    0.88
    bootstrapcdn
    0.86
     myſelf
    0.86
     pleaſure
    0.83
     noDo
    0.81
     مشين
    0.79
    AndEndTag
    0.77
     NSCoder
    0.76
     uſe
    0.74
     ſtand
    0.73
    Activations Density 0.334%

    No Known Activations