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. 15-GEMMASCOPE-RES-16K
    6. 2295
    Prev
    Next
    INDEX
    Explanations

    references to academic qualifications and positions in the medical field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -0.51
     sort
    -0.50
    iš
    -0.45
     actually
    -0.44
    ль
    -0.44
    itte
    -0.44
     page
    -0.43
     plan
    -0.43
     this
    -0.43
    au
    -0.42
    POSITIVE LOGITS
    UnusedPrivate
    0.92
     typelib
    0.82
    TemporalType
    0.81
    __":
    
    0.79
     Савезне
    0.78
    
    0.75
     unknownFields
    0.74
     BoxDecoration
    0.73
    TintMode
    0.73
    ActionCreators
    0.72
    Activations Density 0.179%

    No Known Activations