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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14463
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to property rights and compensation

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

    displacement or forced removal

    np_acts-logits-general · gemini-2.0-flash

    forced eviction or condemnation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.69
    انيف
    -0.58
     Réponses
    -0.57
     <>",
    -0.54
    LookAnd
    -0.52
    jspx
    -0.52
    ScreenState
    -0.51
     cherchés
    -0.50
    出版年
    -0.49
    OrNil
    -0.49
    POSITIVE LOGITS
     displacement
    1.16
     eviction
    1.15
     displaced
    1.10
     displace
    1.04
     evicted
    1.01
     expropri
    1.01
     Displacement
    1.01
     displacements
    0.99
    displacement
    0.95
     forcibly
    0.90
    Activations Density 0.273%

    No Known Activations