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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30169
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "land" in various contexts

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

    land followed by sale or use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parametrize
    -0.49
     veck
    -0.49
     Mukherjee
    -0.48
    #%%
    -0.47
    <bos>
    -0.47
     linkovi
    -0.46
    kio
    -0.45
     teş
    -0.45
    bewer
    -0.44
     Ghosh
    -0.44
    POSITIVE LOGITS
     land
    1.06
     Land
    1.03
    Land
    1.01
     LAND
    0.93
    land
    0.85
     Landry
    0.84
     Landis
    0.77
     lands
    0.76
    Lands
    0.75
     Lands
    0.74
    Activations Density 0.016%

    No Known Activations