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. 5-GEMMASCOPE-RES-16K
    6. 11097
    Prev
    Next
    INDEX
    Explanations

    instances of sending or dispatching people or entities for a purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.61
    contentLoaded
    -0.59
    Przypisy
    -0.56
     виправивши
    -0.53
    ngrx
    -0.48
    sizeCache
    -0.48
    IndentedString
    -0.48
    Referensi
    -0.47
    pran
    -0.46
     Determin
    -0.45
    POSITIVE LOGITS
     OMITBAD
    0.75
    __()
    0.73
     '\\;'
    0.70
    спеди
    0.64
     dispatched
    0.63
    thick
    0.61
     متعلقه
    0.59
    ValueGeneration
    0.58
     tâches
    0.57
     <=",
    0.57
    Activations Density 0.181%

    No Known Activations