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. 8-GEMMASCOPE-RES-16K
    6. 4817
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to layout and styling attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.71
     Boltzmann
    -0.55
    usiai
    -0.55
    haviours
    -0.54
     Taq
    -0.54
     haine
    -0.53
    Build
    -0.51
    IContainer
    -0.51
    ThroughAttribute
    -0.51
    ing
    -0.50
    POSITIVE LOGITS
    fontSize
    0.82
     AssemblyTitle
    0.77
    ymce
    0.70
     propOrder
    0.68
    PyExc
    0.68
     fontSize
    0.67
    Демографія
    0.65
    size
    0.64
     size
    0.62
    StructEnd
    0.62
    Activations Density 0.032%

    No Known Activations