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. 15109
    Prev
    Next
    INDEX
    Explanations

    various efficiency metrics and characteristics related to physical and optical properties in scientific contexts

    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
    petitive
    -0.53
    setSearch
    -0.47
     gött
    -0.47
    NACIONAL
    -0.45
     Elemental
    -0.43
    synchronized
    -0.43
    يد
    -0.43
    Pautan
    -0.42
     elemental
    -0.42
    ريل
    -0.42
    POSITIVE LOGITS
     AssemblyTitle
    0.78
     InputDecoration
    0.77
    DockStyle
    0.73
     hashCode
    0.66
    rrggbb
    0.66
     MessageBoxIcon
    0.65
    SenderId
    0.64
    prefixer
    0.64
    率
    0.64
    AnimationsModule
    0.63
    Activations Density 4.469%

    No Known Activations