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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12617
    Prev
    Next
    INDEX
    Explanations

    themes related to marriage and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.60
    ViewFeatures
    -0.49
     Lokales
    -0.48
    省市镇
    -0.47
     HttpNotFound
    -0.45
    ToAction
    -0.44
    onAttach
    -0.42
     purpoſe
    -0.41
     bombs
    -0.41
    routeProvider
    -0.41
    POSITIVE LOGITS
    Карьера
    0.48
     amistad
    0.40
     flourished
    0.40
    PyErr
    0.40
     survives
    0.39
    
    0.39
     friendships
    0.39
     ended
    0.37
     răsp
    0.37
    netbeans
    0.36
    Activations Density 0.727%

    No Known Activations