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. 1553
    Prev
    Next
    INDEX
    Explanations

    code block endings and method closures in programming syntax

    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
    mato
    -0.49
     
    -0.47
    せ
    -0.45
    YA
    -0.45
    com
    -0.44
    ters
    -0.43
     compa
    -0.42
    ya
    -0.42
     tu
    -0.41
    互
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    1.09
     Exacts
    1.07
     estekak
    1.01
    findpost
    0.99
     الحره
    0.91
    Sucesor
    0.91
     nakalista
    0.89
    webElementXpaths
    0.89
    ngdoc
    0.89
     ProtoMessage
    0.89
    Activations Density 0.033%

    No Known Activations