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. 2-GEMMASCOPE-RES-16K
    6. 2093
    Prev
    Next
    INDEX
    Explanations

    file extension names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bot
    -0.69
    Binding
    -0.67
    DeleteBehavior
    -0.63
     operator
    -0.63
     estekak
    -0.61
     binding
    -0.61
    tagHelperRunner
    -0.60
    Datuak
    -0.60
     Bake
    -0.60
    binding
    -0.60
    POSITIVE LOGITS
    Ext
    0.95
    ext
    0.93
     Ext
    0.83
     citoy
    0.67
     CIT
    0.62
     Diony
    0.61
     violenza
    0.60
    intios
    0.60
     huk
    0.58
     biens
    0.58
    Activations Density 0.038%

    No Known Activations