© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2963
    Prev
    Next
    INDEX
    Explanations

    terms related to structural components and mechanisms in furniture and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific terms related to mechanical components and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.74
    adaptiveStyles
    -0.59
     estekak
    -0.58
    withIdentifier
    -0.55
    StackNavigator
    -0.53
     gainera
    -0.53
     CreateTagHelper
    -0.53
    новниш
    -0.53
     Wicidata
    -0.52
     katal
    -0.51
    POSITIVE LOGITS
     surface
    0.99
     region
    0.91
     portion
    0.88
     section
    0.86
     area
    0.85
     itself
    0.83
     body
    0.80
     face
    0.75
     halves
    0.73
     edge
    0.73
    Activations Density 1.290%

    No Known Activations