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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16158
    Prev
    Next
    INDEX
    Explanations

    references to land, properties, and geographical locations

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

    the word "Land" and its variations or related compound terms.

    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
     MenuView
    -0.43
    gebob
    -0.40
    зулта
    -0.37
    usercontent
    -0.37
    uvwxyz
    -0.37
    setItems
    -0.35
    InputTagHelper
    -0.35
    ecie
    -0.35
    retario
    -0.35
     NOTES
    -0.35
    POSITIVE LOGITS
     Land
    0.75
    Land
    0.73
     land
    0.68
     LAND
    0.58
     Landry
    0.52
    locked
    0.49
    󠁢
    0.48
     viewDidLoad
    0.48
     numerus
    0.47
     landed
    0.46
    Activations Density 0.099%

    No Known Activations