Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 8295
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML structure and scattering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -1.11
    fromCharCode
    -0.99
    BufferException
    -0.98
    RenderAtEndOf
    -0.97
    RegistryLite
    -0.96
    AccessorTable
    -0.95
     esternos
    -0.92
    yntaxException
    -0.91
    Климат
    -0.87
    @[+][
    -0.87
    POSITIVE LOGITS
     scatter
    0.88
    Scatter
    0.78
     Scatter
    0.71
     scattering
    0.70
    scatter
    0.69
     scattered
    0.60
     Scattering
    0.58
    scattering
    0.56
     scat
    0.53
    散
    0.51
    Activations Density 0.011%

    No Known Activations