© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9721
    Prev
    Next
    INDEX
    Explanations

    terms related to marsh habitats and their ecological features

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

    wetland and marsh habitats, particularly in relation to water-logged or boggy environments.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.60
     Infórmanos
    -0.51
     jScrollPane
    -0.44
    Diweddarwch
    -0.44
    Mount
    -0.43
     cliff
    -0.43
    esson
    -0.41
    木坂
    -0.41
     estekak
    -0.40
     Cliff
    -0.40
    POSITIVE LOGITS
     wetlands
    1.15
     wetland
    1.14
     marsh
    1.06
     swamp
    1.05
     Wetlands
    1.04
     marshes
    1.00
     swamps
    0.98
     Wetland
    0.95
    swamp
    0.92
     Swamp
    0.92
    Activations Density 0.176%

    No Known Activations