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. 1-GEMMASCOPE-RES-16K
    6. 6080
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']")
    -1.28
    expandindo
    -1.22
    '):
    
    -1.18
    }")
    
    -1.13
    AccessorTable
    -1.12
    ']))
    
    -1.11
    SharedDtor
    -1.09
    '},
    
    -1.09
    }')
    -1.08
    tagHelperRunner
    -1.08
    POSITIVE LOGITS
    ,
    0.52
    .
    0.45
     [
    0.44
     municípios
    0.42
    /
    0.39
     and
    0.39
    2
    0.39
    ality
    0.39
     famiglie
    0.38
    4
    0.38
    Activations Density 0.248%

    No Known Activations