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. 11-GEMMASCOPE-RES-16K
    6. 1937
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to disputes and disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleins
    -1.00
     AssemblyCulture
    -0.90
     препратки
    -0.90
     שוליים
    -0.84
    fromCharCode
    -0.84
     vectorielle
    -0.83
    SuppressLint
    -0.83
    Varint
    -0.82
    cetin
    -0.81
    tableFuture
    -0.81
    POSITIVE LOGITS
     DIS
    1.38
     Dis
    1.30
    Dis
    1.27
    DIS
    1.26
    dis
    1.19
     useDispatch
    1.17
     dis
    1.04
     Driscoll
    0.95
     dispens
    0.93
     Disqus
    0.92
    Activations Density 0.151%

    No Known Activations