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. 25-GEMMASCOPE-RES-16K
    6. 5932
    Prev
    Next
    INDEX
    Explanations

    descriptions of flavor profiles in food and drink

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.66
     createSlice
    -0.64
    GeneratedCode
    -0.59
    eston
    -0.57
     iprot
    -0.52
    ambique
    -0.52
    review
    -0.52
    })]
    -0.52
    uarts
    -0.51
    DockStyle
    -0.51
    POSITIVE LOGITS
     tang
    0.78
     tart
    0.75
     pe
    0.69
    oredCriteria
    0.68
     sharp
    0.68
     esternos
    0.66
     nutty
    0.64
     sweet
    0.62
     brin
    0.62
    
    0.61
    Activations Density 0.187%

    No Known Activations