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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7308
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to contracts involving real property transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.65
    醐
    -0.60
    sscanf
    -0.50
    yttö
    -0.49
     صوتيه
    -0.49
    basicConfig
    -0.49
     gantung
    -0.48
     trasparente
    -0.48
    testens
    -0.48
    dollis
    -0.47
    POSITIVE LOGITS
     property
    1.54
     assets
    1.46
    property
    1.25
     properties
    1.25
     Assets
    1.16
     Property
    1.15
     PROPERTY
    1.13
    Property
    1.13
     ASSETS
    1.07
     asset
    1.05
    Activations Density 0.386%

    No Known Activations