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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15597
    Prev
    Next
    INDEX
    Explanations

    various types and characteristics of mesh materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.66
    CopyWith
    -0.61
     <=",
    -0.60
     lubricants
    -0.57
     podjela
    -0.57
    ParallelGroup
    -0.56
     lubric
    -0.54
    WriteTagHelper
    -0.53
    WriteAttribute
    -0.51
    getRuntime
    -0.50
    POSITIVE LOGITS
     mesh
    0.91
    adpleegd
    0.87
    MESH
    0.85
     Mesh
    0.82
    mesh
    0.79
     cage
    0.79
     cages
    0.77
     grid
    0.75
    cage
    0.73
     Cage
    0.72
    Activations Density 0.074%

    No Known Activations